mirror of
https://sourceware.org/git/glibc.git
synced 2024-11-24 10:22:41 +08:00
1769608794
Various code in glibc uses __strnlen instead of strnlen for namespace reasons. However, __strnlen does not use libc_hidden_proto / libc_hidden_def (as is normally done for any function defined and called within the same library, whether or not exported from the library and whatever namespace it is in), so the compiler does not know that those calls are to a function within libc. This patch uses libc_hidden_proto / libc_hidden_def with __strnlen. On x86_64, it makes no difference to the installed stripped shared libraries. On 32-bit x86, it causes __strnlen calls to go to the same place as strnlen calls (the fallback strnlen implementation), rather than through a PLT entry for the strnlen IFUNC; I'm not sure of the logic behind when calls from within libc should use IFUNCs versus when they should go direct to a particular function implementation, but clearly it doesn't make sense for strnlen and __strnlen to be handled differently in this regard. Tested for x86_64 and x86 (testsuite, and comparison of installed shared libraries as described above). * string/strnlen.c [!STRNLEN] (__strnlen): Use libc_hidden_def. * include/string.h (__strnlen): Use libc_hidden_proto. * sysdeps/aarch64/strnlen.S (__strnlen): Use libc_hidden_def. * sysdeps/i386/i686/multiarch/strnlen-c.c [SHARED] (libc_hidden_def): Define __GI___strnlen as well as __GI_strnlen. * sysdeps/powerpc/powerpc32/power4/multiarch/strnlen-power7.S (libc_hidden_def): Undefine and redefine. * sysdeps/powerpc/powerpc32/power4/multiarch/strnlen-ppc32.c [SHARED] (libc_hidden_def): Define __GI___strnlen as well as __GI_strnlen. * sysdeps/powerpc/powerpc32/power7/strnlen.S (__strnlen): Use libc_hidden_def. * sysdeps/tile/tilegx/strnlen.c (__strnlen): Likewise.
167 lines
5.2 KiB
C
167 lines
5.2 KiB
C
/* Find the length of STRING, but scan at most MAXLEN characters.
|
|
Copyright (C) 1991-2015 Free Software Foundation, Inc.
|
|
Contributed by Jakub Jelinek <jakub@redhat.com>.
|
|
|
|
Based on strlen written by Torbjorn Granlund (tege@sics.se),
|
|
with help from Dan Sahlin (dan@sics.se);
|
|
commentary by Jim Blandy (jimb@ai.mit.edu).
|
|
|
|
The GNU C Library is free software; you can redistribute it and/or
|
|
modify it under the terms of the GNU Lesser General Public License as
|
|
published by the Free Software Foundation; either version 2.1 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
|
|
Lesser General Public License for more details.
|
|
|
|
You should have received a copy of the GNU Lesser General Public
|
|
License along with the GNU C Library; see the file COPYING.LIB. If
|
|
not, see <http://www.gnu.org/licenses/>. */
|
|
|
|
#include <string.h>
|
|
#include <stdlib.h>
|
|
|
|
/* Find the length of S, but scan at most MAXLEN characters. If no
|
|
'\0' terminator is found in that many characters, return MAXLEN. */
|
|
|
|
#ifdef STRNLEN
|
|
# define __strnlen STRNLEN
|
|
#endif
|
|
|
|
size_t
|
|
__strnlen (const char *str, size_t maxlen)
|
|
{
|
|
const char *char_ptr, *end_ptr = str + maxlen;
|
|
const unsigned long int *longword_ptr;
|
|
unsigned long int longword, himagic, lomagic;
|
|
|
|
if (maxlen == 0)
|
|
return 0;
|
|
|
|
if (__glibc_unlikely (end_ptr < str))
|
|
end_ptr = (const char *) ~0UL;
|
|
|
|
/* Handle the first few characters by reading one character at a time.
|
|
Do this until CHAR_PTR is aligned on a longword boundary. */
|
|
for (char_ptr = str; ((unsigned long int) char_ptr
|
|
& (sizeof (longword) - 1)) != 0;
|
|
++char_ptr)
|
|
if (*char_ptr == '\0')
|
|
{
|
|
if (char_ptr > end_ptr)
|
|
char_ptr = end_ptr;
|
|
return char_ptr - str;
|
|
}
|
|
|
|
/* All these elucidatory comments refer to 4-byte longwords,
|
|
but the theory applies equally well to 8-byte longwords. */
|
|
|
|
longword_ptr = (unsigned long int *) char_ptr;
|
|
|
|
/* 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. */
|
|
himagic = 0x80808080L;
|
|
lomagic = 0x01010101L;
|
|
if (sizeof (longword) > 4)
|
|
{
|
|
/* 64-bit version of the magic. */
|
|
/* Do the shift in two steps to avoid a warning if long has 32 bits. */
|
|
himagic = ((himagic << 16) << 16) | himagic;
|
|
lomagic = ((lomagic << 16) << 16) | lomagic;
|
|
}
|
|
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. */
|
|
while (longword_ptr < (unsigned long int *) end_ptr)
|
|
{
|
|
/* 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. */
|
|
|
|
longword = *longword_ptr++;
|
|
|
|
if ((longword - lomagic) & himagic)
|
|
{
|
|
/* Which of the bytes was the zero? If none of them were, it was
|
|
a misfire; continue the search. */
|
|
|
|
const char *cp = (const char *) (longword_ptr - 1);
|
|
|
|
char_ptr = cp;
|
|
if (cp[0] == 0)
|
|
break;
|
|
char_ptr = cp + 1;
|
|
if (cp[1] == 0)
|
|
break;
|
|
char_ptr = cp + 2;
|
|
if (cp[2] == 0)
|
|
break;
|
|
char_ptr = cp + 3;
|
|
if (cp[3] == 0)
|
|
break;
|
|
if (sizeof (longword) > 4)
|
|
{
|
|
char_ptr = cp + 4;
|
|
if (cp[4] == 0)
|
|
break;
|
|
char_ptr = cp + 5;
|
|
if (cp[5] == 0)
|
|
break;
|
|
char_ptr = cp + 6;
|
|
if (cp[6] == 0)
|
|
break;
|
|
char_ptr = cp + 7;
|
|
if (cp[7] == 0)
|
|
break;
|
|
}
|
|
}
|
|
char_ptr = end_ptr;
|
|
}
|
|
|
|
if (char_ptr > end_ptr)
|
|
char_ptr = end_ptr;
|
|
return char_ptr - str;
|
|
}
|
|
#ifndef STRNLEN
|
|
libc_hidden_def (__strnlen)
|
|
weak_alias (__strnlen, strnlen)
|
|
#endif
|
|
libc_hidden_def (strnlen)
|