linux_dsm_epyc7002/arch/csky/abiv2/memcpy.S
Guo Ren 35ff802af1 csky: fixup remove vdsp implement for kernel.
The vr regs for vdsp only saved in task_switch not in every
exception trap-in. The memcpy with vdsp instructions will
destroy the vr regs for user space applications.

Signed-off-by: Guo Ren <ren_guo@c-sky.com>
2018-12-31 22:56:59 +08:00

105 lines
1.9 KiB
ArmAsm

/* SPDX-License-Identifier: GPL-2.0 */
// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
#include <linux/linkage.h>
#include "sysdep.h"
ENTRY(__memcpy)
ENTRY(memcpy)
/* Test if len less than 4 bytes. */
mov r12, r0
cmplti r2, 4
bt .L_copy_by_byte
andi r13, r0, 3
movi r19, 4
/* Test if dest is not 4 bytes aligned. */
bnez r13, .L_dest_not_aligned
/* Hardware can handle unaligned access directly. */
.L_dest_aligned:
/* If dest is aligned, then copy. */
zext r18, r2, 31, 4
/* Test if len less than 16 bytes. */
bez r18, .L_len_less_16bytes
movi r19, 0
LABLE_ALIGN
.L_len_larger_16bytes:
#if defined(__CK860__)
ldw r3, (r1, 0)
stw r3, (r0, 0)
ldw r3, (r1, 4)
stw r3, (r0, 4)
ldw r3, (r1, 8)
stw r3, (r0, 8)
ldw r3, (r1, 12)
addi r1, 16
stw r3, (r0, 12)
addi r0, 16
#else
ldw r20, (r1, 0)
ldw r21, (r1, 4)
ldw r22, (r1, 8)
ldw r23, (r1, 12)
stw r20, (r0, 0)
stw r21, (r0, 4)
stw r22, (r0, 8)
stw r23, (r0, 12)
PRE_BNEZAD (r18)
addi r1, 16
addi r0, 16
#endif
BNEZAD (r18, .L_len_larger_16bytes)
.L_len_less_16bytes:
zext r18, r2, 3, 2
bez r18, .L_copy_by_byte
.L_len_less_16bytes_loop:
ldw r3, (r1, 0)
PRE_BNEZAD (r18)
addi r1, 4
stw r3, (r0, 0)
addi r0, 4
BNEZAD (r18, .L_len_less_16bytes_loop)
/* Test if len less than 4 bytes. */
.L_copy_by_byte:
zext r18, r2, 1, 0
bez r18, .L_return
.L_copy_by_byte_loop:
ldb r3, (r1, 0)
PRE_BNEZAD (r18)
addi r1, 1
stb r3, (r0, 0)
addi r0, 1
BNEZAD (r18, .L_copy_by_byte_loop)
.L_return:
mov r0, r12
rts
/*
* If dest is not aligned, just copying some bytes makes the
* dest align.
*/
.L_dest_not_aligned:
sub r13, r19, r13
sub r2, r13
/* Makes the dest align. */
.L_dest_not_aligned_loop:
ldb r3, (r1, 0)
PRE_BNEZAD (r13)
addi r1, 1
stb r3, (r0, 0)
addi r0, 1
BNEZAD (r13, .L_dest_not_aligned_loop)
cmplti r2, 4
bt .L_copy_by_byte
/* Check whether the src is aligned. */
jbr .L_dest_aligned
ENDPROC(__memcpy)