xref: /linux/arch/riscv/kernel/vec-copy-unaligned.S (revision c1668520c9aa4019738f27097b187a5460646cbc)
1/* SPDX-License-Identifier: GPL-2.0 */
2/* Copyright (C) 2024 Rivos Inc. */
3
4#include <linux/args.h>
5#include <linux/linkage.h>
6#include <asm/asm.h>
7
8	.text
9
10#define WORD_EEW 32
11
12#define WORD_SEW CONCATENATE(e, WORD_EEW)
13#define VEC_L CONCATENATE(vle, WORD_EEW).v
14#define VEC_S CONCATENATE(vle, WORD_EEW).v
15
16/* void __riscv_copy_vec_words_unaligned(void *, const void *, size_t) */
17/* Performs a memcpy without aligning buffers, using word loads and stores. */
18/* Note: The size is truncated to a multiple of WORD_EEW */
19SYM_FUNC_START(__riscv_copy_vec_words_unaligned)
20	andi  a4, a2, ~(WORD_EEW-1)
21	beqz  a4, 2f
22	add   a3, a1, a4
23	.option push
24	.option arch, +zve32x
251:
26	vsetivli t0, 8, WORD_SEW, m8, ta, ma
27	VEC_L v0, (a1)
28	VEC_S v0, (a0)
29	addi  a0, a0, WORD_EEW
30	addi  a1, a1, WORD_EEW
31	bltu  a1, a3, 1b
32
332:
34	.option pop
35	ret
36SYM_FUNC_END(__riscv_copy_vec_words_unaligned)
37
38/* void __riscv_copy_vec_bytes_unaligned(void *, const void *, size_t) */
39/* Performs a memcpy without aligning buffers, using only byte accesses. */
40/* Note: The size is truncated to a multiple of 8 */
41SYM_FUNC_START(__riscv_copy_vec_bytes_unaligned)
42	andi a4, a2, ~(8-1)
43	beqz a4, 2f
44	add  a3, a1, a4
45	.option push
46	.option arch, +zve32x
471:
48	vsetivli t0, 8, e8, m8, ta, ma
49	vle8.v v0, (a1)
50	vse8.v v0, (a0)
51	addi a0, a0, 8
52	addi a1, a1, 8
53	bltu a1, a3, 1b
54
552:
56	.option pop
57	ret
58SYM_FUNC_END(__riscv_copy_vec_bytes_unaligned)
59