mirror of
https://sourceware.org/git/glibc.git
synced 2025-01-13 12:40:08 +00:00
6d52618b15
Thu Dec 19 23:28:33 1996 Ulrich Drepper <drepper@cygnus.com> * resolv/resolv.h: Update from BIND 4.9.5-P1. * resolv/res_comp.c: Likewise. * resolv/res_debug.c: Likewise. * resolv/Banner: Update version number. Thu Dec 19 20:58:53 1996 Ulrich Drepper <drepper@cygnus.com> * elf/dlfcn.h: Add extern "C" wrapper. * io/utime.h: Don't define NULL since this isn't allowed in POSIX. * io/sys/stat.h: Declare `lstat' only if __USE_BSD || __USE_XOPEN_EXTENDED. * locale/locale.h: Define NULL. * math/math.c: Don't include <errno.h> to define math errors. * stdlib/stdlib.h: Likewise. * posix/unistd.h: Don't declare environ. * posix/sys/utsname.h (struct utsname): Declare member domainname as __domainname is !__USE_GNU. * signal/signal.h: Declare size_t only if __USE_BSD || __USE_XOPEN_EXTENDED. * stdio/stdio.h: Don't declare cuserid when __USE_POSIX, but instead when __USE_XOPEN. * string/string.h: Define strndup only if __USE_GNU. * sysdeps/unix/sysv/linux/clock.c: New file. * sysdeps/unix/sysv/linux/timebits.h: Define CLOCKS_PER_SEC as 1000000 per X/Open standard. * features.h: Add code to recognize _POSIX_C_SOURCE value 199309. Define __USE_POSIX199309. * posix/unistd.h: Declare fdatasync only if __USE_POSIX199309. * time/time.c: Declare nanosleep only if __USE_POSIX199309. Patches by Rüdiger Helsch <rh@unifix.de>. * locale/locale.h: Add declaration of newlocale and freelocale. * new-malloc/Makefile (distibute): Add mtrace.awk. (dist-routines): Add mcheck and mtrace. (install-lib, non-lib.a): Define as libmcheck.a. * new-malloc/malloc.h: Add declaration of __malloc_initialized. * new-malloc/mcheck.c: New file. * new-malloc/mcheck.h: New file. * new-malloc/mtrace.c: New file. * new-malloc/mtrace.awk: New file. * posix/unistd.h: Correct prototype for usleep. * sysdeps/unix/bsd/usleep.c: De-ANSI-declfy. Correct return type. * sysdeps/unix/sysv/linux/usleep.c: Real implementation based on nanosleep. * signal/signal.h: Change protoype of __sigpause to take two arguments. Remove prototype for sigpause. Add two different macros named sigpause selected when __USE_BSD or __USE_XOPEN are defined. This is necessary since the old BSD definition of theis function collides with the X/Open definition. * sysdeps/posix/sigpause.c: Change function definition to also fit X/Open definition. * sysdeps/libm-i387/e_exp.S: Make sure stack is empty when the function is left. * sysdeps/libm-i387/e_expl.S: Likewise. Patch by HJ Lu. 1996-12-17 Paul Eggert <eggert@twinsun.com> * many, many files: Spelling corrections. * catgets/catgetsinfo.h (mmapped): Renamed from mmaped (in struct catalog_info.status). * mach/err_kern.sub (err_codes_unix), string/stratcliff.c (main): Fix spelling in message. * po/libc.pot: Fix spelling in message for `zic'; this anticipates a fix in the tzcode distribution. Wed Dec 18 15:48:02 1996 Ulrich Drepper <drepper@cygnus.com> * time/strftime.c: Implement ^ flag to cause output be converted to use upper case characters. * time/zic.c: Update from ADO tzcode1996n. Wed Dec 18 14:29:24 1996 Erik Naggum <erik@naggum.no> * time/strftime.c (add): Don't change global `i' until all is over. Define NULL is not already defined. Tue Dec 17 09:49:03 1996 Andreas Schwab <schwab@issan.informatik.uni-dortmund.de> * libio/iovsprintf.c (_IO_vsprintf): Change `&sf' to `&sf._sbf._f' to avoid the need for a cast. * libio/iovsscanf.c (_IO_vsscanf): Likewise. * sunrpc/rpc/xdr.h: Add prototype for xdr_free.
184 lines
5.5 KiB
ArmAsm
184 lines
5.5 KiB
ArmAsm
/* strlen -- Compute length og NUL terminated string.
|
|
Highly optimized version for ix86, x>=5.
|
|
Copyright (C) 1995, 1996 Free Software Foundation, Inc.
|
|
This file is part of the GNU C Library.
|
|
Contributed by Ulrich Drepper, <drepper@gnu.ai.mit.edu>.
|
|
|
|
The GNU C Library is free software; you can redistribute it and/or
|
|
modify it under the terms of the GNU Library General Public License as
|
|
published by the Free Software Foundation; either version 2 of the
|
|
License, or (at your option) any later version.
|
|
|
|
The GNU C Library is distributed in the hope that it will be useful,
|
|
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
Library General Public License for more details.
|
|
|
|
You should have received a copy of the GNU Library General Public
|
|
License along with the GNU C Library; see the file COPYING.LIB. If not,
|
|
write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
|
|
Boston, MA 02111-1307, USA. */
|
|
|
|
#include <sysdep.h>
|
|
|
|
/* This version is especially optimized for the i586 (and following?)
|
|
processors. This is mainly done by using the two pipelines. The
|
|
version optimized for i486 is weak in this aspect because to get
|
|
as much parallelism we have to execute some *more* instructions.
|
|
|
|
The code below is structured to reflect the pairing of the instructions
|
|
as *I think* it is. I have no processor data book to verify this.
|
|
If you find something you think is incorrect let me know. */
|
|
|
|
|
|
/* The magic value which is used throughout in the whole code. */
|
|
#define magic 0xfefefeff
|
|
|
|
/*
|
|
INPUT PARAMETERS:
|
|
str (sp + 4)
|
|
*/
|
|
|
|
.text
|
|
ENTRY(strlen)
|
|
movl 4(%esp), %eax /* get string pointer */
|
|
movl $3, %edx /* load mask (= 3) */
|
|
|
|
andl %eax, %edx /* separate last two bits of address */
|
|
|
|
jz L1 /* aligned => start loop */
|
|
jp L0 /* exactly two bits set */
|
|
|
|
cmpb %dh, (%eax) /* is byte NUL? */
|
|
je L2 /* yes => return */
|
|
|
|
incl %eax /* increment pointer */
|
|
cmpb %dh, (%eax) /* is byte NUL? */
|
|
|
|
je L2 /* yes => return */
|
|
|
|
incl %eax /* increment pointer */
|
|
xorl $2, %edx
|
|
|
|
jz L1
|
|
|
|
L0: cmpb %dh, (%eax) /* is byte NUL? */
|
|
je L2 /* yes => return */
|
|
|
|
incl %eax /* increment pointer */
|
|
xorl %edx, %edx /* We need %edx == 0 for later */
|
|
|
|
/* We exit the loop if adding MAGIC_BITS to LONGWORD fails to
|
|
change any of the hole bits of LONGWORD.
|
|
|
|
1) Is this safe? Will it catch all the zero bytes?
|
|
Suppose there is a byte with all zeros. Any carry bits
|
|
propagating from its left will fall into the hole at its
|
|
least significant bit and stop. Since there will be no
|
|
carry from its most significant bit, the LSB of the
|
|
byte to the left will be unchanged, and the zero will be
|
|
detected.
|
|
|
|
2) Is this worthwhile? Will it ignore everything except
|
|
zero bytes? Suppose every byte of LONGWORD has a bit set
|
|
somewhere. There will be a carry into bit 8. If bit 8
|
|
is set, this will carry into bit 16. If bit 8 is clear,
|
|
one of bits 9-15 must be set, so there will be a carry
|
|
into bit 16. Similarly, there will be a carry into bit
|
|
24. If one of bits 24-31 is set, there will be a carry
|
|
into bit 32 (=carry flag), so all of the hole bits will
|
|
be changed.
|
|
|
|
Note: %edx == 0 in any case here. */
|
|
|
|
L1:
|
|
movl (%eax), %ecx /* get word (= 4 bytes) in question */
|
|
addl $4, %eax /* adjust pointer for *next* word */
|
|
|
|
subl %ecx, %edx /* first step to negate word */
|
|
addl $magic, %ecx /* add magic word */
|
|
|
|
decl %edx /* complete negation of word */
|
|
jnc L3 /* previous addl caused overflow? */
|
|
|
|
xorl %ecx, %edx /* (word+magic)^word */
|
|
|
|
andl $~magic, %edx /* any of the carry flags set? */
|
|
|
|
jne L3 /* yes => determine byte */
|
|
|
|
|
|
movl (%eax), %ecx /* get word (= 4 bytes) in question */
|
|
addl $4, %eax /* adjust pointer for *next* word */
|
|
|
|
subl %ecx, %edx /* first step to negate word */
|
|
addl $magic, %ecx /* add magic word */
|
|
|
|
decl %edx /* complete negation of word */
|
|
jnc L3 /* previous addl caused overflow? */
|
|
|
|
xorl %ecx, %edx /* (word+magic)^word */
|
|
|
|
andl $~magic, %edx /* any of the carry flags set? */
|
|
|
|
jne L3 /* yes => determine byte */
|
|
|
|
|
|
movl (%eax), %ecx /* get word (= 4 bytes) in question */
|
|
addl $4, %eax /* adjust pointer for *next* word */
|
|
|
|
subl %ecx, %edx /* first step to negate word */
|
|
addl $magic, %ecx /* add magic word */
|
|
|
|
decl %edx /* complete negation of word */
|
|
jnc L3 /* previous addl caused overflow? */
|
|
|
|
xorl %ecx, %edx /* (word+magic)^word */
|
|
|
|
andl $~magic, %edx /* any of the carry flags set? */
|
|
|
|
jne L3 /* yes => determine byte */
|
|
|
|
|
|
movl (%eax), %ecx /* get word (= 4 bytes) in question */
|
|
addl $4, %eax /* adjust pointer for *next* word */
|
|
|
|
subl %ecx, %edx /* first step to negate word */
|
|
addl $magic, %ecx /* add magic word */
|
|
|
|
decl %edx /* complete negation of word */
|
|
jnc L3 /* previous addl caused overflow? */
|
|
|
|
xorl %ecx, %edx /* (word+magic)^word */
|
|
|
|
andl $~magic, %edx /* any of the carry flags set? */
|
|
|
|
je L1 /* no => start loop again */
|
|
|
|
|
|
L3: subl $4, %eax /* correct too early pointer increment */
|
|
subl $magic, %ecx
|
|
|
|
cmpb $0, %cl /* lowest byte NUL? */
|
|
jz L2 /* yes => return */
|
|
|
|
inc %eax /* increment pointer */
|
|
testb %ch, %ch /* second byte NUL? */
|
|
|
|
jz L2 /* yes => return */
|
|
|
|
shrl $16, %ecx /* make upper bytes accessible */
|
|
incl %eax /* increment pointer */
|
|
|
|
cmpb $0, %cl /* is third byte NUL? */
|
|
jz L2 /* yes => return */
|
|
|
|
incl %eax /* increment pointer */
|
|
|
|
L2: subl 4(%esp), %eax /* now compute the length as difference
|
|
between start and terminating NUL
|
|
character */
|
|
|
|
ret
|
|
END (strlen)
|