riscv: assembler versions of memcpy, memmove, memset

Provide optimized versions of memcpy(), memmove(), memset() copied from
the Linux kernel.

Signed-off-by: Heinrich Schuchardt <xypron.glpk@gmx.de>
Reviewed-by: Leo Yu-Chi Liang <ycliang@andestech.com>
diff --git a/arch/riscv/lib/memmove.S b/arch/riscv/lib/memmove.S
new file mode 100644
index 0000000..07d1d21
--- /dev/null
+++ b/arch/riscv/lib/memmove.S
@@ -0,0 +1,64 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <linux/linkage.h>
+#include <asm/asm.h>
+
+ENTRY(__memmove)
+WEAK(memmove)
+        move    t0, a0
+        move    t1, a1
+
+        beq     a0, a1, exit_memcpy
+        beqz    a2, exit_memcpy
+        srli    t2, a2, 0x2
+
+        slt     t3, a0, a1
+        beqz    t3, do_reverse
+
+        andi    a2, a2, 0x3
+        li      t4, 1
+        beqz    t2, byte_copy
+
+word_copy:
+        lw      t3, 0(a1)
+        addi    t2, t2, -1
+        addi    a1, a1, 4
+        sw      t3, 0(a0)
+        addi    a0, a0, 4
+        bnez    t2, word_copy
+        beqz    a2, exit_memcpy
+        j       byte_copy
+
+do_reverse:
+        add     a0, a0, a2
+        add     a1, a1, a2
+        andi    a2, a2, 0x3
+        li      t4, -1
+        beqz    t2, reverse_byte_copy
+
+reverse_word_copy:
+        addi    a1, a1, -4
+        addi    t2, t2, -1
+        lw      t3, 0(a1)
+        addi    a0, a0, -4
+        sw      t3, 0(a0)
+        bnez    t2, reverse_word_copy
+        beqz    a2, exit_memcpy
+
+reverse_byte_copy:
+        addi    a0, a0, -1
+        addi    a1, a1, -1
+
+byte_copy:
+        lb      t3, 0(a1)
+        addi    a2, a2, -1
+        sb      t3, 0(a0)
+        add     a1, a1, t4
+        add     a0, a0, t4
+        bnez    a2, byte_copy
+
+exit_memcpy:
+        move a0, t0
+        move a1, t1
+        ret
+END(__memmove)