;------------------------------------------------------------------------------
|
;
|
; Copyright (c) 2006, Intel Corporation. All rights reserved.<BR>
|
; SPDX-License-Identifier: BSD-2-Clause-Patent
|
;
|
; Module Name:
|
;
|
; CopyMem.nasm
|
;
|
; Abstract:
|
;
|
; CopyMem function
|
;
|
; Notes:
|
;
|
;------------------------------------------------------------------------------
|
|
SECTION .text
|
|
;------------------------------------------------------------------------------
|
; VOID *
|
; InternalMemCopyMem (
|
; IN VOID *Destination,
|
; IN VOID *Source,
|
; IN UINTN Count
|
; );
|
;------------------------------------------------------------------------------
|
global ASM_PFX(InternalMemCopyMem)
|
ASM_PFX(InternalMemCopyMem):
|
push esi
|
push edi
|
mov esi, [esp + 16] ; esi <- Source
|
mov edi, [esp + 12] ; edi <- Destination
|
mov edx, [esp + 20] ; edx <- Count
|
lea eax, [esi + edx - 1] ; eax <- End of Source
|
cmp esi, edi
|
jae .0
|
cmp eax, edi ; Overlapped?
|
jae @CopyBackward ; Copy backward if overlapped
|
.0:
|
xor ecx, ecx
|
sub ecx, edi
|
and ecx, 15 ; ecx + edi aligns on 16-byte boundary
|
jz .1
|
cmp ecx, edx
|
cmova ecx, edx
|
sub edx, ecx ; edx <- remaining bytes to copy
|
rep movsb
|
.1:
|
mov ecx, edx
|
and edx, 15
|
shr ecx, 4 ; ecx <- # of DQwords to copy
|
jz @CopyBytes
|
add esp, -16
|
movdqu [esp], xmm0 ; save xmm0
|
.2:
|
movdqu xmm0, [esi] ; esi may not be 16-bytes aligned
|
movntdq [edi], xmm0 ; edi should be 16-bytes aligned
|
add esi, 16
|
add edi, 16
|
loop .2
|
mfence
|
movdqu xmm0, [esp] ; restore xmm0
|
add esp, 16 ; stack cleanup
|
jmp @CopyBytes
|
@CopyBackward:
|
mov esi, eax ; esi <- Last byte in Source
|
lea edi, [edi + edx - 1] ; edi <- Last byte in Destination
|
std
|
@CopyBytes:
|
mov ecx, edx
|
rep movsb
|
cld
|
mov eax, [esp + 12] ; eax <- Destination as return value
|
pop edi
|
pop esi
|
ret
|
|
