166 lines
4.5 KiB
ArmAsm
166 lines
4.5 KiB
ArmAsm
|
/* $NetBSD: strlen.S,v 1.1 2005/12/20 19:28:50 christos Exp $ */
|
||
|
|
||
|
/*
|
||
|
* Copyright 2002 Wasabi Systems, Inc.
|
||
|
* All rights reserved.
|
||
|
*
|
||
|
* Written by Eduardo Horvath for Wasabi Systems, Inc.
|
||
|
*
|
||
|
* 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. All advertising materials mentioning features or use of this software
|
||
|
* must display the following acknowledgement:
|
||
|
* This product includes software developed for the NetBSD Project by
|
||
|
* Wasabi Systems, Inc.
|
||
|
* 4. The name of Wasabi Systems, Inc. may not be used to endorse
|
||
|
* or promote products derived from this software without specific prior
|
||
|
* written permission.
|
||
|
*
|
||
|
* THIS SOFTWARE IS PROVIDED BY WASABI SYSTEMS, INC. ``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 WASABI SYSTEMS, INC
|
||
|
* 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>
|
||
|
#if defined(LIBC_SCCS) && !defined(lint)
|
||
|
RCSID("$NetBSD: strlen.S,v 1.1 2005/12/20 19:28:50 christos Exp $")
|
||
|
#endif /* LIBC_SCCS and not lint */
|
||
|
|
||
|
/* The algorithm here uses the following techniques:
|
||
|
*
|
||
|
* 1) Given a word 'x', we can test to see if it contains any 0 bytes
|
||
|
* by subtracting 0x01010101, and seeing if any of the high bits of each
|
||
|
* byte changed from 0 to 1. This works because the least significant
|
||
|
* 0 byte must have had no incoming carry (otherwise it's not the least
|
||
|
* significant), so it is 0x00 - 0x01 == 0xff. For all other
|
||
|
* byte values, either they have the high bit set initially, or when
|
||
|
* 1 is subtracted you get a value in the range 0x00-0x7f, none of which
|
||
|
* have their high bit set. The expression here is
|
||
|
* (x + 0xfefefeff) & ~(x | 0x7f7f7f7f), which gives 0x00000000 when
|
||
|
* there were no 0x00 bytes in the word.
|
||
|
*
|
||
|
* 2) Now just hunt for the first byte that's 0x00 in 'x'.
|
||
|
*
|
||
|
* This is from the book 'The PowerPC Compiler Writer's Guide',
|
||
|
* by Steve Hoxey, Faraydon Karim, Bill Hay and Hank Warren.
|
||
|
*/
|
||
|
|
||
|
ENTRY(strlen)
|
||
|
/*
|
||
|
* Calculate address for and load the first xword.
|
||
|
*/
|
||
|
andn %o0, 0x7, %o1
|
||
|
ldx [%o1], %g1
|
||
|
|
||
|
/*
|
||
|
* Now prepare some constants while the data arrives...
|
||
|
*/
|
||
|
sethi %hi(0xfefefefe), %o3
|
||
|
sethi %hi(0x7f7f7f7f), %o2
|
||
|
|
||
|
or %o3, %lo(0xfefefefe), %o3
|
||
|
or %o2, %lo(0x7f7f7f7f), %o2
|
||
|
|
||
|
sllx %o3, 32, %o5
|
||
|
andcc %o0, 0x7, %g5 ! Hoisted from below to fill a slot
|
||
|
|
||
|
sllx %o2, 32, %o4
|
||
|
or %o3, %o5, %o3
|
||
|
|
||
|
sll %g5, 3, %g5 ! Convert to bytes. hoisted
|
||
|
or %o2, %o4, %o2
|
||
|
|
||
|
inc %o3
|
||
|
neg %g5 ! hoisted
|
||
|
|
||
|
/*
|
||
|
* Mask off the leading bits:
|
||
|
*
|
||
|
* if (ptr & 0x7)
|
||
|
* mask = -1 << (64 - ((ptr & 0x7) << 3));
|
||
|
*/
|
||
|
|
||
|
! andcc %o0, 0x7, %g5 ! Hoisted above
|
||
|
bz,pt %icc, 0f
|
||
|
|
||
|
|
||
|
! sll %g5, 3, %g5 ! Convert to bytes. Also hoisted
|
||
|
|
||
|
! neg %g5 ! Hoisted
|
||
|
|
||
|
add %g5, 64, %g5
|
||
|
mov -1, %o4
|
||
|
|
||
|
sllx %o4, %g5, %o4
|
||
|
|
||
|
or %o4, %g1, %g1 ! Make leading bytes != 0
|
||
|
|
||
|
0:
|
||
|
or %g1, %o2, %o5 ! Do step 1 -- use or/andn instead of nor/and
|
||
|
add %g1, %o3, %g5
|
||
|
|
||
|
inc 8, %o1 ! Point to next word
|
||
|
andncc %g5, %o5, %g0
|
||
|
bz,a,pt %xcc, 0b
|
||
|
ldx [%o1], %g1
|
||
|
|
||
|
mov -1, %o4
|
||
|
dec 8, %o1
|
||
|
|
||
|
sllx %o4, 64-8, %o5
|
||
|
|
||
|
btst %g1, %o5 ! Check high byte
|
||
|
bz %xcc,0f
|
||
|
srlx %o5, 8, %o5
|
||
|
|
||
|
inc %o1
|
||
|
btst %g1, %o5 ! Check 2nd byte
|
||
|
bz %xcc,0f
|
||
|
srlx %o5, 8, %o5
|
||
|
|
||
|
inc %o1
|
||
|
btst %g1, %o5 ! Check 3rd byte
|
||
|
bz %xcc,0f
|
||
|
srlx %o5, 8, %o5
|
||
|
|
||
|
inc %o1
|
||
|
btst %g1, %o5 ! Check 4th byte
|
||
|
bz %xcc,0f
|
||
|
srlx %o5, 8, %o5
|
||
|
|
||
|
inc %o1
|
||
|
btst %g1, %o5 ! Check 5th byte
|
||
|
bz %xcc,0f
|
||
|
srlx %o5, 8, %o5
|
||
|
|
||
|
inc %o1
|
||
|
btst %g1, %o5 ! Check 6th byte
|
||
|
bz %xcc,0f
|
||
|
srlx %o5, 8, %o5
|
||
|
|
||
|
inc %o1
|
||
|
btst %g1, %o5 ! Check 7th byte
|
||
|
bz %xcc,0f
|
||
|
nop
|
||
|
|
||
|
inc %o1
|
||
|
0:
|
||
|
retl
|
||
|
sub %o1, %o0, %o0 ! return length (ptr - (origptr+1))
|