arch/loongarch/lib/memset.S

/* SPDX-License-Identifier: GPL-2.0 */
/*
 * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
 */

#include <linux/export.h>
#include <asm/alternative-asm.h>
#include <asm/asm.h>
#include <asm/asmmacro.h>
#include <asm/cpu.h>
#include <asm/regdef.h>
#include <asm/unwind_hints.h>

.macro fill_to_64 r0
	bstrins.d \r0, \r0, 15, 8
	bstrins.d \r0, \r0, 31, 16
	bstrins.d \r0, \r0, 63, 32
.endm

.section .noinstr.text, "ax"

SYM_FUNC_START(memset)
	/*
	 * Some CPUs support hardware unaligned access
	 */
	ALTERNATIVE	"b __memset_generic", \
			"b __memset_fast", CPU_FEATURE_UAL
SYM_FUNC_END(memset)
SYM_FUNC_ALIAS(__memset, memset)

EXPORT_SYMBOL(memset)
EXPORT_SYMBOL(__memset)

_ASM_NOKPROBE(memset)
_ASM_NOKPROBE(__memset)

/*
 * void *__memset_generic(void *s, int c, size_t n)
 *
 * a0: s
 * a1: c
 * a2: n
 */
SYM_FUNC_START(__memset_generic)
	move	a3, a0
	beqz	a2, 2f

1:	st.b	a1, a0, 0
	addi.d	a0, a0, 1
	addi.d	a2, a2, -1
	bgt	a2, zero, 1b

2:	move	a0, a3
	jr	ra
SYM_FUNC_END(__memset_generic)
_ASM_NOKPROBE(__memset_generic)

/*
 * void *__memset_fast(void *s, int c, size_t n)
 *
 * a0: s
 * a1: c
 * a2: n
 */
SYM_FUNC_START(__memset_fast)
	/* fill a1 to 64 bits */
	fill_to_64 a1

	sltui	t0, a2, 9
	bnez	t0, .Lsmall

	add.d	a2, a0, a2
	st.d	a1, a0, 0

	/* align up address */
	addi.d	a3, a0, 8
	bstrins.d	a3, zero, 2, 0

	addi.d	a4, a2, -64
	bgeu	a3, a4, .Llt64

	/* set 64 bytes at a time */
.Lloop64:
	st.d	a1, a3, 0
	st.d	a1, a3, 8
	st.d	a1, a3, 16
	st.d	a1, a3, 24
	st.d	a1, a3, 32
	st.d	a1, a3, 40
	st.d	a1, a3, 48
	st.d	a1, a3, 56
	addi.d	a3, a3, 64
	bltu	a3, a4, .Lloop64

	/* set the remaining bytes */
.Llt64:
	addi.d	a4, a2, -32
	bgeu	a3, a4, .Llt32
	st.d	a1, a3, 0
	st.d	a1, a3, 8
	st.d	a1, a3, 16
	st.d	a1, a3, 24
	addi.d	a3, a3, 32

.Llt32:
	addi.d	a4, a2, -16
	bgeu	a3, a4, .Llt16
	st.d	a1, a3, 0
	st.d	a1, a3, 8
	addi.d	a3, a3, 16

.Llt16:
	addi.d	a4, a2, -8
	bgeu	a3, a4, .Llt8
	st.d	a1, a3, 0

.Llt8:
	st.d	a1, a2, -8

	/* return */
	jr	ra

	.align	4
.Lsmall:
	pcaddi	t0, 4
	slli.d	a2, a2, 4
	add.d	t0, t0, a2
	jr	t0

	.align	4
0:	jr	ra

	.align	4
1:	st.b	a1, a0, 0
	jr	ra

	.align	4
2:	st.h	a1, a0, 0
	jr	ra

	.align	4
3:	st.h	a1, a0, 0
	st.b	a1, a0, 2
	jr	ra

	.align	4
4:	st.w	a1, a0, 0
	jr	ra

	.align	4
5:	st.w	a1, a0, 0
	st.b	a1, a0, 4
	jr	ra

	.align	4
6:	st.w	a1, a0, 0
	st.h	a1, a0, 4
	jr	ra

	.align	4
7:	st.w	a1, a0, 0
	st.w	a1, a0, 3
	jr	ra

	.align	4
8:	st.d	a1, a0, 0
	jr	ra
SYM_FUNC_END(__memset_fast)
_ASM_NOKPROBE(__memset_fast)

STACK_FRAME_NON_STANDARD __memset_fast