mirror of
https://sourceware.org/git/glibc.git
synced 2024-11-09 23:00:07 +00:00
string: Improve generic strchrnul
New algorithm read the first aligned address and mask off the unwanted bytes (this strategy is similar to arch-specific implementations used on powerpc, sparc, and sh). The loop now read word-aligned address and check using the has_zero_eq function. Checked on x86_64-linux-gnu, i686-linux-gnu, powerpc64-linux-gnu, and powerpc-linux-gnu by removing the arch-specific assembly implementation and disabling multi-arch (it covers both LE and BE for 64 and 32 bits). Co-authored-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Noah Goldstein <goldstein.w.n@gmail.com>
This commit is contained in:
parent
350d8d1366
commit
685e844a97
@ -1,10 +1,5 @@
|
|||||||
/* Copyright (C) 1991-2023 Free Software Foundation, Inc.
|
/* Copyright (C) 1991-2023 Free Software Foundation, Inc.
|
||||||
This file is part of the GNU C Library.
|
This file is part of the GNU C Library.
|
||||||
Based on strlen implementation by Torbjorn Granlund (tege@sics.se),
|
|
||||||
with help from Dan Sahlin (dan@sics.se) and
|
|
||||||
bug fix and commentary by Jim Blandy (jimb@ai.mit.edu);
|
|
||||||
adaptation to strchr suggested by Dick Karpinski (dick@cca.ucsf.edu),
|
|
||||||
and implemented by Roland McGrath (roland@ai.mit.edu).
|
|
||||||
|
|
||||||
The GNU C Library is free software; you can redistribute it and/or
|
The GNU C Library is free software; you can redistribute it and/or
|
||||||
modify it under the terms of the GNU Lesser General Public
|
modify it under the terms of the GNU Lesser General Public
|
||||||
@ -20,147 +15,41 @@
|
|||||||
License along with the GNU C Library; if not, see
|
License along with the GNU C Library; if not, see
|
||||||
<https://www.gnu.org/licenses/>. */
|
<https://www.gnu.org/licenses/>. */
|
||||||
|
|
||||||
|
#include <libc-pointer-arith.h>
|
||||||
|
#include <string-fzb.h>
|
||||||
|
#include <string-fzc.h>
|
||||||
|
#include <string-fzi.h>
|
||||||
|
#include <string-shift.h>
|
||||||
#include <string.h>
|
#include <string.h>
|
||||||
#include <memcopy.h>
|
|
||||||
#include <stdlib.h>
|
|
||||||
|
|
||||||
#undef __strchrnul
|
#undef __strchrnul
|
||||||
#undef strchrnul
|
#undef strchrnul
|
||||||
|
|
||||||
#ifndef STRCHRNUL
|
#ifdef STRCHRNUL
|
||||||
# define STRCHRNUL __strchrnul
|
# define __strchrnul STRCHRNUL
|
||||||
#endif
|
#endif
|
||||||
|
|
||||||
/* Find the first occurrence of C in S or the final NUL byte. */
|
/* Find the first occurrence of C in S or the final NUL byte. */
|
||||||
char *
|
char *
|
||||||
STRCHRNUL (const char *s, int c_in)
|
__strchrnul (const char *str, int c_in)
|
||||||
{
|
{
|
||||||
const unsigned char *char_ptr;
|
/* Align pointer to sizeof op_t. */
|
||||||
const unsigned long int *longword_ptr;
|
uintptr_t s_int = (uintptr_t) str;
|
||||||
unsigned long int longword, magic_bits, charmask;
|
const op_t *word_ptr = (const op_t *) PTR_ALIGN_DOWN (str, sizeof (op_t));
|
||||||
unsigned char c;
|
|
||||||
|
|
||||||
c = (unsigned char) c_in;
|
op_t repeated_c = repeat_bytes (c_in);
|
||||||
|
|
||||||
/* Handle the first few characters by reading one character at a time.
|
op_t word = *word_ptr;
|
||||||
Do this until CHAR_PTR is aligned on a longword boundary. */
|
find_t mask = shift_find (find_zero_eq_all (word, repeated_c), s_int);
|
||||||
for (char_ptr = (const unsigned char *) s;
|
if (mask != 0)
|
||||||
((unsigned long int) char_ptr & (sizeof (longword) - 1)) != 0;
|
return (char *) str + index_first (mask);
|
||||||
++char_ptr)
|
|
||||||
if (*char_ptr == c || *char_ptr == '\0')
|
|
||||||
return (void *) char_ptr;
|
|
||||||
|
|
||||||
/* All these elucidatory comments refer to 4-byte longwords,
|
do
|
||||||
but the theory applies equally well to 8-byte longwords. */
|
word = *++word_ptr;
|
||||||
|
while (! has_zero_eq (word, repeated_c));
|
||||||
|
|
||||||
longword_ptr = (unsigned long int *) char_ptr;
|
return (char *) word_ptr + index_first_zero_eq (word, repeated_c);
|
||||||
|
|
||||||
/* Bits 31, 24, 16, and 8 of this number are zero. Call these bits
|
|
||||||
the "holes." Note that there is a hole just to the left of
|
|
||||||
each byte, with an extra at the end:
|
|
||||||
|
|
||||||
bits: 01111110 11111110 11111110 11111111
|
|
||||||
bytes: AAAAAAAA BBBBBBBB CCCCCCCC DDDDDDDD
|
|
||||||
|
|
||||||
The 1-bits make sure that carries propagate to the next 0-bit.
|
|
||||||
The 0-bits provide holes for carries to fall into. */
|
|
||||||
magic_bits = -1;
|
|
||||||
magic_bits = magic_bits / 0xff * 0xfe << 1 >> 1 | 1;
|
|
||||||
|
|
||||||
/* Set up a longword, each of whose bytes is C. */
|
|
||||||
charmask = c | (c << 8);
|
|
||||||
charmask |= charmask << 16;
|
|
||||||
if (sizeof (longword) > 4)
|
|
||||||
/* Do the shift in two steps to avoid a warning if long has 32 bits. */
|
|
||||||
charmask |= (charmask << 16) << 16;
|
|
||||||
if (sizeof (longword) > 8)
|
|
||||||
abort ();
|
|
||||||
|
|
||||||
/* Instead of the traditional loop which tests each character,
|
|
||||||
we will test a longword at a time. The tricky part is testing
|
|
||||||
if *any of the four* bytes in the longword in question are zero. */
|
|
||||||
for (;;)
|
|
||||||
{
|
|
||||||
/* We tentatively 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 24-30 is set, there will be a carry
|
|
||||||
into bit 31, so all of the hole bits will be changed.
|
|
||||||
|
|
||||||
The one misfire occurs when bits 24-30 are clear and bit
|
|
||||||
31 is set; in this case, the hole at bit 31 is not
|
|
||||||
changed. If we had access to the processor carry flag,
|
|
||||||
we could close this loophole by putting the fourth hole
|
|
||||||
at bit 32!
|
|
||||||
|
|
||||||
So it ignores everything except 128's, when they're aligned
|
|
||||||
properly.
|
|
||||||
|
|
||||||
3) But wait! Aren't we looking for C as well as zero?
|
|
||||||
Good point. So what we do is XOR LONGWORD with a longword,
|
|
||||||
each of whose bytes is C. This turns each byte that is C
|
|
||||||
into a zero. */
|
|
||||||
|
|
||||||
longword = *longword_ptr++;
|
|
||||||
|
|
||||||
/* Add MAGIC_BITS to LONGWORD. */
|
|
||||||
if ((((longword + magic_bits)
|
|
||||||
|
|
||||||
/* Set those bits that were unchanged by the addition. */
|
|
||||||
^ ~longword)
|
|
||||||
|
|
||||||
/* Look at only the hole bits. If any of the hole bits
|
|
||||||
are unchanged, most likely one of the bytes was a
|
|
||||||
zero. */
|
|
||||||
& ~magic_bits) != 0
|
|
||||||
|
|
||||||
/* That caught zeroes. Now test for C. */
|
|
||||||
|| ((((longword ^ charmask) + magic_bits) ^ ~(longword ^ charmask))
|
|
||||||
& ~magic_bits) != 0)
|
|
||||||
{
|
|
||||||
/* Which of the bytes was C or zero?
|
|
||||||
If none of them were, it was a misfire; continue the search. */
|
|
||||||
|
|
||||||
const unsigned char *cp = (const unsigned char *) (longword_ptr - 1);
|
|
||||||
|
|
||||||
if (*cp == c || *cp == '\0')
|
|
||||||
return (char *) cp;
|
|
||||||
if (*++cp == c || *cp == '\0')
|
|
||||||
return (char *) cp;
|
|
||||||
if (*++cp == c || *cp == '\0')
|
|
||||||
return (char *) cp;
|
|
||||||
if (*++cp == c || *cp == '\0')
|
|
||||||
return (char *) cp;
|
|
||||||
if (sizeof (longword) > 4)
|
|
||||||
{
|
|
||||||
if (*++cp == c || *cp == '\0')
|
|
||||||
return (char *) cp;
|
|
||||||
if (*++cp == c || *cp == '\0')
|
|
||||||
return (char *) cp;
|
|
||||||
if (*++cp == c || *cp == '\0')
|
|
||||||
return (char *) cp;
|
|
||||||
if (*++cp == c || *cp == '\0')
|
|
||||||
return (char *) cp;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
/* This should never happen. */
|
|
||||||
return NULL;
|
|
||||||
}
|
}
|
||||||
|
#ifndef STRCHRNUL
|
||||||
weak_alias (__strchrnul, strchrnul)
|
weak_alias (__strchrnul, strchrnul)
|
||||||
|
#endif
|
||||||
|
@ -19,10 +19,6 @@
|
|||||||
#include <string.h>
|
#include <string.h>
|
||||||
|
|
||||||
#define STRCHRNUL __strchrnul_ppc
|
#define STRCHRNUL __strchrnul_ppc
|
||||||
|
|
||||||
#undef weak_alias
|
|
||||||
#define weak_alias(a,b )
|
|
||||||
|
|
||||||
extern __typeof (strchrnul) __strchrnul_ppc attribute_hidden;
|
extern __typeof (strchrnul) __strchrnul_ppc attribute_hidden;
|
||||||
|
|
||||||
#include <string/strchrnul.c>
|
#include <string/strchrnul.c>
|
||||||
|
@ -22,8 +22,6 @@
|
|||||||
# if HAVE_STRCHRNUL_IFUNC
|
# if HAVE_STRCHRNUL_IFUNC
|
||||||
# define STRCHRNUL STRCHRNUL_C
|
# define STRCHRNUL STRCHRNUL_C
|
||||||
# define __strchrnul STRCHRNUL
|
# define __strchrnul STRCHRNUL
|
||||||
# undef weak_alias
|
|
||||||
# define weak_alias(name, alias)
|
|
||||||
# endif
|
# endif
|
||||||
|
|
||||||
# include <string/strchrnul.c>
|
# include <string/strchrnul.c>
|
||||||
|
Loading…
Reference in New Issue
Block a user