/*
* 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
* 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
*/
/*
*/
/*
* memcpy(s1, s2, len)
*
* Copy s2 to s1, always copy n bytes.
* Note: this does not work for overlapped copies, bcopy() does
*
* Fast assembler language version of the following C-program for memcpy
* which represents the `standard' for the C-library.
*
* void *
* memcpy(void *s, const void *s0, size_t n)
* {
* if (n != 0) {
* char *s1 = s;
* const char *s2 = s0;
* do {
* *s1++ = *s2++;
* } while (--n != 0);
* }
* return (s);
* }
*/
#include "SYS.h"
inc 2, %o0
dec 2, %o2
.aldst: andcc %o0, 3, %o5 ! align the destination address
.ald: bz .w4cp
cmp %o5, 2
bz .w2cp
cmp %o5, 3
.w3cp: ld [%o1], %o4
inc 4, %o1
srl %o4, 24, %o5
stb %o5, [%o0]
bne .w1cp
inc %o0
dec 1, %o2
andn %o2, 3, %o3 ! o3 is aligned word count
dec 4, %o3 ! avoid reading beyond tail of src
sub %o1, %o0, %o1 ! o1 gets the difference
1: sll %o4, 8, %g1 ! save residual bytes
ld [%o1+%o0], %o4
deccc 4, %o3
srl %o4, 24, %o5 ! merge with residual
or %o5, %g1, %g1
st %g1, [%o0]
bnz 1b
inc 4, %o0
sub %o1, 3, %o1 ! used one byte of last word read
and %o2, 3, %o2
b 7f
inc 4, %o2
.w1cp: srl %o4, 8, %o5
sth %o5, [%o0]
inc 2, %o0
dec 3, %o2
andn %o2, 3, %o3 ! o3 is aligned word count
dec 4, %o3 ! avoid reading beyond tail of src
sub %o1, %o0, %o1 ! o1 gets the difference
2: sll %o4, 24, %g1 ! save residual bytes
ld [%o1+%o0], %o4
deccc 4, %o3
srl %o4, 8, %o5 ! merge with residual
or %o5, %g1, %g1
st %g1, [%o0]
bnz 2b
inc 4, %o0
sub %o1, 1, %o1 ! used three bytes of last word read
and %o2, 3, %o2
b 7f
inc 4, %o2
.w2cp: ld [%o1], %o4
inc 4, %o1
srl %o4, 16, %o5
sth %o5, [%o0]
inc 2, %o0
dec 2, %o2
andn %o2, 3, %o3 ! o3 is aligned word count
dec 4, %o3 ! avoid reading beyond tail of src
sub %o1, %o0, %o1 ! o1 gets the difference
3: sll %o4, 16, %g1 ! save residual bytes
ld [%o1+%o0], %o4
deccc 4, %o3
srl %o4, 16, %o5 ! merge with residual
or %o5, %g1, %g1
st %g1, [%o0]
bnz 3b
inc 4, %o0
sub %o1, 2, %o1 ! used two bytes of last word read
and %o2, 3, %o2
b 7f
inc 4, %o2
.w4cp: andn %o2, 3, %o3 ! o3 is aligned word count
sub %o1, %o0, %o1 ! o1 gets the difference
1: ld [%o1+%o0], %o4 ! read from address
deccc 4, %o3 ! decrement count
st %o4, [%o0] ! write at destination address
bgu 1b
inc 4, %o0 ! increment to address
b 7f
and %o2, 3, %o2 ! number of leftover bytes, if any
!
! differenced byte copy, works with any alignment
!
.dbytecp:
b 7f
sub %o1, %o0, %o1 ! o1 gets the difference
4: stb %o4, [%o0] ! write to address
inc %o0 ! inc to address
7: deccc %o2 ! decrement count
bgeu,a 4b ! loop till done
ldub [%o1+%o0], %o4 ! read from address
retl
ld [%sp + 68], %o0 ! return s1, destination address
SET_SIZE(memcpy)