/*-
 * Copyright (c) 2018 Instituto de Pesquisas Eldorado
 * All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 * 3. Neither the name of the author nor the names of its contributors may
 *    be used to endorse or promote products derived from this software
 *
 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 */

#include <machine/asm.h>
ENTRY(__strncpy_arch_2_05)
        stdu    %r1,-40(%r1)
        mflr    %r0
        std     %r0,16(%r1)
        std     %r3,32(%r1)

        xor     %r6,%r6,%r6     /* fixed 0 reg */

/* align loop */
        addi    %r3,%r3,-1
.Lalign_loop:
        /* len? */
        cmpdi   %r5,0
        beq     .Lexit
        /* aligned? */
        andi.   %r0,%r4,7
        beq     .Ldw_copy
        /* copy */
        lbz     %r7,0(%r4)
        stbu    %r7,1(%r3)
        addi    %r4,%r4,1
        addi    %r5,%r5,-1
        /* zero? */
        cmpdi   %r7,0
        beq     .Lzero
        b       .Lalign_loop

/* dword copy loop */
.Ldw_copy:
        /* prepare src and dst to use load/store and update */
        addi    %r3,%r3,-7
        addi    %r4,%r4,-8
.Ldw_copy_loop:
        cmpdi   %r5,8
        blt     .Lbyte_copy

        ldu     %r0,8(%r4)
        /* check for 0 */
        cmpb    %r7,%r0,%r6
        cmpdi   %r7,0
        bne     .Lbyte_copy_and_zero
        /* copy to dst */
        stdu    %r0,8(%r3)
        addi    %r5,%r5,-8
        b       .Ldw_copy_loop

/* Copy remaining src bytes, zero-out buffer
 * Note: r5 will be >= 8
 */
.Lbyte_copy_and_zero:
        addi    %r3,%r3,7
        addi    %r4,%r4,-1
.Lbyte_copy_and_zero_loop:
        lbzu    %r7,1(%r4)
        stbu    %r7,1(%r3)
        addi    %r5,%r5,-1
        cmpdi   %r7,0
        beq     .Lzero
        b       .Lbyte_copy_and_zero_loop

/* zero-out remaining dst bytes */
.Lzero:
        addi    %r3,%r3,1
        li      %r4,0
        /* r5 has len already */
        bl      memset
        nop
        b       .Lexit

/* copy remaining (< 8) bytes */
.Lbyte_copy:
        cmpdi   %r5,0
        beq     .Lexit
        addi    %r3,%r3,7
        addi    %r4,%r4,7
        mtctr   %r5
.Lbyte_copy_loop:
        lbzu    %r7,1(%r4)
        stbu    %r7,1(%r3)
        cmpdi   %r7,0
        /* 0 found: zero out remaining bytes */
        beq     .Lbyte_copy_zero
        bdnz    .Lbyte_copy_loop
        b       .Lexit
.Lbyte_copy_zero_loop:
        stbu    %r6,1(%r3)
.Lbyte_copy_zero:
        bdnz    .Lbyte_copy_zero_loop

.Lexit:
        /* epilogue */
        ld      %r3,32(%r1)
        ld      %r0,16(%r1)
        mtlr    %r0
        addi    %r1,%r1,40
        blr

END(__strncpy_arch_2_05)

        .section .note.GNU-stack,"",%progbits