* Maksym Planeta <mcsim.planeta@xxxxxxxxx> wrote:
> For x86 architecture get_order function can be optimized due to
> assembler instruction bsr.
>
> This is second version of patch where for constants gcc precompute the
> result.
>
> Signed-off-by: Maksym Planeta <mcsim.planeta@xxxxxxxxx>
> ---
> arch/x86/include/asm/getorder.h | 48 +++++++++++++++++++++++++++++++++++++++
> arch/x86/include/asm/page.h | 2 +-
> 2 files changed, 49 insertions(+), 1 deletions(-)
> create mode 100644 arch/x86/include/asm/getorder.h
>
> diff --git a/arch/x86/include/asm/getorder.h b/arch/x86/include/asm/getorder.h
> new file mode 100644
> index 0000000..b0c6f57
> --- /dev/null
> +++ b/arch/x86/include/asm/getorder.h
> @@ -0,0 +1,48 @@
> +#ifndef __ASM_GENERIC_GETORDER_H
> +#define __ASM_GENERIC_GETORDER_H
> +
> +#ifndef __ASSEMBLY__
> +
> +#include <linux/compiler.h>
> +
> +#ifdef CONFIG_X86_CMOV
> +#define ASM_CMOVZ(op, dest) \
> + "cmovzl %" #op ",%" #dest ";\n\t"
> +#else
> +#define ASM_CMOVZ(op, dest) \
> + "jnz 1f;\n\t" \
> + "movl %" #op ", %" #dest ";\n\t" \
> + "1: "
> +#endif
> +
> +static __always_inline int __get_order(unsigned long size)
> +{
> + int order;
> +
> + size = (size - 1) >> (PAGE_SHIFT - 1);
> + asm("bsr %1, %0\n\t"
> + ASM_CMOVZ(2, 0)
> + : "=&r" (order) : "rm" (size), "rm" (0));
> + return order;
> +}
> +
> +/* Pure 2^n version of get_order */
> +static inline __attribute_const__ int get_order(unsigned long size)
> +{
> + int order;
> +
> + if (__builtin_constant_p(size)) {
> + size = (size - 1) >> (PAGE_SHIFT - 1);
> + order = -1;
> + do {
> + size >>= 1;
> + order++;
> + } while (size);
> + return order;
> + }
> + return __get_order(size);
> +}
> +
> +#endif /* __ASSEMBLY__ */
> +
> +#endif /* __ASM_GENERIC_GETORDER_H */
> diff --git a/arch/x86/include/asm/page.h b/arch/x86/include/asm/page.h
> index 8ca8283..10e4c45 100644
> --- a/arch/x86/include/asm/page.h
> +++ b/arch/x86/include/asm/page.h
> @@ -63,7 +63,7 @@ extern bool __virt_addr_valid(unsigned long kaddr);
> #endif /* __ASSEMBLY__ */
>
> #include <asm-generic/memory_model.h>
> -#include <asm-generic/getorder.h>
> +#include <asm/getorder.h>
Just wondering, what's the before/after 'size vmlinux' effect on a 'make
defconfig' x86 kernel? Does the optimization make the kernel smaller as well,
besides making it faster?
Thanks,
Ingo
--
To unsubscribe from this list: send the line "unsubscribe kernel-janitors" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
