/*
 * CDDL HEADER START
 *
 * The contents of this file are subject to the terms of the
 * Common Development and Distribution License (the "License").
 * You may not use this file except in compliance with the License.
 *
 * You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
 * or http://www.opensolaris.org/os/licensing.
 * See the License for the specific language governing permissions
 * and limitations under the License.
 *
 * When distributing Covered Code, include this CDDL HEADER in each
 * file and include the License file at usr/src/OPENSOLARIS.LICENSE.
 * If applicable, add the following below this CDDL HEADER, with the
 * fields enclosed by brackets "[]" replaced with your own identifying
 * information: Portions Copyright [yyyy] [name of copyright owner]
 *
 * CDDL HEADER END
 */
/*
 * Copyright 2004 Sun Microsystems, Inc.  All rights reserved.
 * Use is subject to license terms.
 */

        .file   "strcat.s"

/
/ strcat(s1, s2)
/
/ Concatenates s2 on the end of s1.  s1's space must be large enough.
/ Returns s1.
/
/ Fast assembly language version of the following C-program strcat
/ which represents the `standard' for the C-library.
/
/       char *
/       strcat(char *s1, const char *s2)
/       {
/               char    *os1 = s1;
/
/               while (*s1++)
/                       ;
/               --s1;
/               while (*s1++ = *s2++)
/                       ;
/               return (os1);
/       }
/
/ In this assembly language version, the following expression is used
/ to check if a 32-bit word data contains a null byte or not:
/       (((A & 0x7f7f7f7f) + 0x7f7f7f7f) | A) & 0x80808080
/ If the above expression geneates a value other than 0x80808080,
/ that means the 32-bit word data contains a null byte.
/

#include "SYS.h"

        ENTRY(strcat)
        pushl   %edi                    / save register variable
        / find a null byte in destination string
        movl    8(%esp), %edi           / %edi = destination string address
        testl   $3, %edi                / if %edi not word aligned
        jnz     .L1                     / goto .L1
        .align  4
.L2:
        movl    (%edi), %edx            / move 1 word from (%edi) to %edx
        movl    $0x7f7f7f7f, %ecx
        andl    %edx, %ecx              / %ecx = %edx & 0x7f7f7f7f
        addl    $4, %edi                / next word
        addl    $0x7f7f7f7f, %ecx       / %ecx += 0x7f7f7f7f
        orl     %edx, %ecx              / %ecx |= %edx
        andl    $0x80808080, %ecx       / %ecx &= 0x80808080
        cmpl    $0x80808080, %ecx       / if no null byte in this word
        je      .L2                     / goto .L2
        subl    $4, %edi                / post-incremented
.L1:
        cmpb    $0, (%edi)              / if a byte in (%edi) is null
        je      .L3                     / goto .L3
        incl    %edi                    / next byte
        testl   $3, %edi                / if %edi not word aligned
        jnz     .L1                     / goto .L1
        jmp     .L2                     / goto .L2 (%edi word aligned)
        .align  4
.L3:
        / %edi points to a null byte in destination string
        movl    12(%esp), %eax          / %eax = source string address
        testl   $3, %eax                / if %eax not word aligned
        jnz     .L4                     / goto .L4
        .align  4
.L5:
        movl    (%eax), %edx            / move 1 word from (%eax) to %edx
        movl    $0x7f7f7f7f, %ecx
        andl    %edx, %ecx              / %ecx = %edx & 0x7f7f7f7f
        addl    $4, %eax                / next word
        addl    $0x7f7f7f7f, %ecx       / %ecx += 0x7f7f7f7f
        orl     %edx, %ecx              / %ecx |= %edx
        andl    $0x80808080, %ecx       / %ecx &= 0x80808080
        cmpl    $0x80808080, %ecx       / if null byte in this word
        jne     .L7                     / goto .L7
        movl    %edx, (%edi)            / copy this word to (%edi)
        addl    $4, %edi                / next word
        jmp     .L5                     / goto .L5
.L7:
        subl    $4, %eax                / post-incremented
        .align  4
.L4:
        movb    (%eax), %dl             / %dl = a byte in (%eax)
        cmpb    $0, %dl                 / compare %dl with a null byte
        movb    %dl, (%edi)             / copy %dl to (%edi)
        je      .L6                     / if %dl is a null, goto .L6
        incl    %eax                    / next byte
        incl    %edi                    / next byte
        testl   $3, %eax                / if %eax not word aligned
        jnz     .L4                     / goto .L4
        jmp     .L5                     / goto .L5 (%eax word aligned)
        .align  4
.L6:
        movl    8(%esp), %eax           / return the destination address
        popl    %edi                    / restore register variable
        ret
        SET_SIZE(strcat)