/* SPDX-License-Identifier: GPL-2.0 */
/* Copyright (C) 2023 Rivos Inc. */

#include <linux/linkage.h>
#include <asm/asm.h>

        .text

/* void __riscv_copy_words_unaligned(void *, const void *, size_t) */
/* Performs a memcpy without aligning buffers, using word loads and stores. */
/* Note: The size is truncated to a multiple of 8 * SZREG */
SYM_FUNC_START(__riscv_copy_words_unaligned)
        andi  a4, a2, ~((8*SZREG)-1)
        beqz  a4, 2f
        add   a3, a1, a4
1:
        REG_L a4,       0(a1)
        REG_L a5,   SZREG(a1)
        REG_L a6, 2*SZREG(a1)
        REG_L a7, 3*SZREG(a1)
        REG_L t0, 4*SZREG(a1)
        REG_L t1, 5*SZREG(a1)
        REG_L t2, 6*SZREG(a1)
        REG_L t3, 7*SZREG(a1)
        REG_S a4,       0(a0)
        REG_S a5,   SZREG(a0)
        REG_S a6, 2*SZREG(a0)
        REG_S a7, 3*SZREG(a0)
        REG_S t0, 4*SZREG(a0)
        REG_S t1, 5*SZREG(a0)
        REG_S t2, 6*SZREG(a0)
        REG_S t3, 7*SZREG(a0)
        addi  a0, a0, 8*SZREG
        addi  a1, a1, 8*SZREG
        bltu  a1, a3, 1b

2:
        ret
SYM_FUNC_END(__riscv_copy_words_unaligned)

/* void __riscv_copy_bytes_unaligned(void *, const void *, size_t) */
/* Performs a memcpy without aligning buffers, using only byte accesses. */
/* Note: The size is truncated to a multiple of 8 */
SYM_FUNC_START(__riscv_copy_bytes_unaligned)
        andi a4, a2, ~(8-1)
        beqz a4, 2f
        add  a3, a1, a4
1:
        lb   a4, 0(a1)
        lb   a5, 1(a1)
        lb   a6, 2(a1)
        lb   a7, 3(a1)
        lb   t0, 4(a1)
        lb   t1, 5(a1)
        lb   t2, 6(a1)
        lb   t3, 7(a1)
        sb   a4, 0(a0)
        sb   a5, 1(a0)
        sb   a6, 2(a0)
        sb   a7, 3(a0)
        sb   t0, 4(a0)
        sb   t1, 5(a0)
        sb   t2, 6(a0)
        sb   t3, 7(a0)
        addi a0, a0, 8
        addi a1, a1, 8
        bltu a1, a3, 1b

2:
        ret
SYM_FUNC_END(__riscv_copy_bytes_unaligned)