linux/arch/x86/lib/hweight.S
Linus Torvalds 84d69848c9 Merge branch 'kbuild' of git://git.kernel.org/pub/scm/linux/kernel/git/mmarek/kbuild
Pull kbuild updates from Michal Marek:

 - EXPORT_SYMBOL for asm source by Al Viro.

   This does bring a regression, because genksyms no longer generates
   checksums for these symbols (CONFIG_MODVERSIONS). Nick Piggin is
   working on a patch to fix this.

   Plus, we are talking about functions like strcpy(), which rarely
   change prototypes.

 - Fixes for PPC fallout of the above by Stephen Rothwell and Nick
   Piggin

 - fixdep speedup by Alexey Dobriyan.

 - preparatory work by Nick Piggin to allow architectures to build with
   -ffunction-sections, -fdata-sections and --gc-sections

 - CONFIG_THIN_ARCHIVES support by Stephen Rothwell

 - fix for filenames with colons in the initramfs source by me.

* 'kbuild' of git://git.kernel.org/pub/scm/linux/kernel/git/mmarek/kbuild: (22 commits)
  initramfs: Escape colons in depfile
  ppc: there is no clear_pages to export
  powerpc/64: whitelist unresolved modversions CRCs
  kbuild: -ffunction-sections fix for archs with conflicting sections
  kbuild: add arch specific post-link Makefile
  kbuild: allow archs to select link dead code/data elimination
  kbuild: allow architectures to use thin archives instead of ld -r
  kbuild: Regenerate genksyms lexer
  kbuild: genksyms fix for typeof handling
  fixdep: faster CONFIG_ search
  ia64: move exports to definitions
  sparc32: debride memcpy.S a bit
  [sparc] unify 32bit and 64bit string.h
  sparc: move exports to definitions
  ppc: move exports to definitions
  arm: move exports to definitions
  s390: move exports to definitions
  m68k: move exports to definitions
  alpha: move exports to actual definitions
  x86: move exports to actual definitions
  ...
2016-10-14 14:26:58 -07:00

83 lines
2.4 KiB
ArmAsm

#include <linux/linkage.h>
#include <asm/export.h>
#include <asm/asm.h>
/*
* unsigned int __sw_hweight32(unsigned int w)
* %rdi: w
*/
ENTRY(__sw_hweight32)
#ifdef CONFIG_X86_64
movl %edi, %eax # w
#endif
__ASM_SIZE(push,) %__ASM_REG(dx)
movl %eax, %edx # w -> t
shrl %edx # t >>= 1
andl $0x55555555, %edx # t &= 0x55555555
subl %edx, %eax # w -= t
movl %eax, %edx # w -> t
shrl $2, %eax # w_tmp >>= 2
andl $0x33333333, %edx # t &= 0x33333333
andl $0x33333333, %eax # w_tmp &= 0x33333333
addl %edx, %eax # w = w_tmp + t
movl %eax, %edx # w -> t
shrl $4, %edx # t >>= 4
addl %edx, %eax # w_tmp += t
andl $0x0f0f0f0f, %eax # w_tmp &= 0x0f0f0f0f
imull $0x01010101, %eax, %eax # w_tmp *= 0x01010101
shrl $24, %eax # w = w_tmp >> 24
__ASM_SIZE(pop,) %__ASM_REG(dx)
ret
ENDPROC(__sw_hweight32)
EXPORT_SYMBOL(__sw_hweight32)
ENTRY(__sw_hweight64)
#ifdef CONFIG_X86_64
pushq %rdi
pushq %rdx
movq %rdi, %rdx # w -> t
movabsq $0x5555555555555555, %rax
shrq %rdx # t >>= 1
andq %rdx, %rax # t &= 0x5555555555555555
movabsq $0x3333333333333333, %rdx
subq %rax, %rdi # w -= t
movq %rdi, %rax # w -> t
shrq $2, %rdi # w_tmp >>= 2
andq %rdx, %rax # t &= 0x3333333333333333
andq %rdi, %rdx # w_tmp &= 0x3333333333333333
addq %rdx, %rax # w = w_tmp + t
movq %rax, %rdx # w -> t
shrq $4, %rdx # t >>= 4
addq %rdx, %rax # w_tmp += t
movabsq $0x0f0f0f0f0f0f0f0f, %rdx
andq %rdx, %rax # w_tmp &= 0x0f0f0f0f0f0f0f0f
movabsq $0x0101010101010101, %rdx
imulq %rdx, %rax # w_tmp *= 0x0101010101010101
shrq $56, %rax # w = w_tmp >> 56
popq %rdx
popq %rdi
ret
#else /* CONFIG_X86_32 */
/* We're getting an u64 arg in (%eax,%edx): unsigned long hweight64(__u64 w) */
pushl %ecx
call __sw_hweight32
movl %eax, %ecx # stash away result
movl %edx, %eax # second part of input
call __sw_hweight32
addl %ecx, %eax # result
popl %ecx
ret
#endif
ENDPROC(__sw_hweight64)
EXPORT_SYMBOL(__sw_hweight64)