string/rawmemchr.c

   1 /* Copyright (C) 1991,93,96,97,99,2000,2002,2012 Free Software Foundation, Inc.
   2    This file is part of the GNU C Library.
   3    Based on strlen implementation by Torbjorn Granlund (tege@sics.se),
   4    with help from Dan Sahlin (dan@sics.se) and
   5    commentary by Jim Blandy (jimb@ai.mit.edu);
   6    adaptation to memchr suggested by Dick Karpinski (dick@cca.ucsf.edu),
   7    and implemented by Roland McGrath (roland@ai.mit.edu).
   8
   9    The GNU C Library is free software; you can redistribute it and/or
  10    modify it under the terms of the GNU Lesser General Public
  11    License as published by the Free Software Foundation; either
  12    version 2.1 of the License, or (at your option) any later version.
  13
  14    The GNU C Library is distributed in the hope that it will be useful,
  15    but WITHOUT ANY WARRANTY; without even the implied warranty of
  16    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  17    Lesser General Public License for more details.
  18
  19    You should have received a copy of the GNU Lesser General Public
  20    License along with the GNU C Library; if not, see
  21    <http://www.gnu.org/licenses/>.  */
  22
  23 #ifdef HAVE_CONFIG_H
  24 #include <config.h>
  25 #endif
  26
  27 #undef __ptr_t
  28 #define __ptr_t void *
  29
  30 #if defined (_LIBC)
  31 # include <string.h>
  32 # include <memcopy.h>
  33 # include <stdlib.h>
  34 #endif
  35
  36 #if defined (HAVE_LIMITS_H) || defined (_LIBC)
  37 # include <limits.h>
  38 #endif
  39
  40 #define LONG_MAX_32_BITS 2147483647
  41
  42 #ifndef LONG_MAX
  43 #define LONG_MAX LONG_MAX_32_BITS
  44 #endif
  45
  46 #include <sys/types.h>
  47
  48 #undef memchr
  49
  50
  51 /* Find the first occurrence of C in S.  */
  52 __ptr_t
  53 __rawmemchr (s, c_in)
  54      const __ptr_t s;
  55      int c_in;
  56 {
  57   const unsigned char *char_ptr;
  58   const unsigned long int *longword_ptr;
  59   unsigned long int longword, magic_bits, charmask;
  60   unsigned char c;
  61
  62   c = (unsigned char) c_in;
  63
  64   /* Handle the first few characters by reading one character at a time.
  65      Do this until CHAR_PTR is aligned on a longword boundary.  */
  66   for (char_ptr = (const unsigned char *) s;
  67        ((unsigned long int) char_ptr & (sizeof (longword) - 1)) != 0;
  68        ++char_ptr)
  69     if (*char_ptr == c)
  70       return (__ptr_t) char_ptr;
  71
  72   /* All these elucidatory comments refer to 4-byte longwords,
  73      but the theory applies equally well to 8-byte longwords.  */
  74
  75   longword_ptr = (unsigned long int *) char_ptr;
  76
  77   /* Bits 31, 24, 16, and 8 of this number are zero.  Call these bits
  78      the "holes."  Note that there is a hole just to the left of
  79      each byte, with an extra at the end:
  80
  81      bits:  01111110 11111110 11111110 11111111
  82      bytes: AAAAAAAA BBBBBBBB CCCCCCCC DDDDDDDD
  83
  84      The 1-bits make sure that carries propagate to the next 0-bit.
  85      The 0-bits provide holes for carries to fall into.  */
  86
  87   if (sizeof (longword) != 4 && sizeof (longword) != 8)
  88     abort ();
  89
  90 #if LONG_MAX <= LONG_MAX_32_BITS
  91   magic_bits = 0x7efefeff;
  92 #else
  93   magic_bits = ((unsigned long int) 0x7efefefe << 32) | 0xfefefeff;
  94 #endif
  95
  96   /* Set up a longword, each of whose bytes is C.  */
  97   charmask = c | (c << 8);
  98   charmask |= charmask << 16;
  99 #if LONG_MAX > LONG_MAX_32_BITS
 100   charmask |= charmask << 32;
 101 #endif
 102
 103   /* Instead of the traditional loop which tests each character,
 104      we will test a longword at a time.  The tricky part is testing
 105      if *any of the four* bytes in the longword in question are zero.  */
 106   while (1)
 107     {
 108       /* We tentatively exit the loop if adding MAGIC_BITS to
 109          LONGWORD fails to change any of the hole bits of LONGWORD.
 110
 111          1) Is this safe?  Will it catch all the zero bytes?
 112          Suppose there is a byte with all zeros.  Any carry bits
 113          propagating from its left will fall into the hole at its
 114          least significant bit and stop.  Since there will be no
 115          carry from its most significant bit, the LSB of the
 116          byte to the left will be unchanged, and the zero will be
 117          detected.
 118
 119          2) Is this worthwhile?  Will it ignore everything except
 120          zero bytes?  Suppose every byte of LONGWORD has a bit set
 121          somewhere.  There will be a carry into bit 8.  If bit 8
 122          is set, this will carry into bit 16.  If bit 8 is clear,
 123          one of bits 9-15 must be set, so there will be a carry
 124          into bit 16.  Similarly, there will be a carry into bit
 125          24.  If one of bits 24-30 is set, there will be a carry
 126          into bit 31, so all of the hole bits will be changed.
 127
 128          The one misfire occurs when bits 24-30 are clear and bit
 129          31 is set; in this case, the hole at bit 31 is not
 130          changed.  If we had access to the processor carry flag,
 131          we could close this loophole by putting the fourth hole
 132          at bit 32!
 133
 134          So it ignores everything except 128's, when they're aligned
 135          properly.
 136
 137          3) But wait!  Aren't we looking for C, not zero?
 138          Good point.  So what we do is XOR LONGWORD with a longword,
 139          each of whose bytes is C.  This turns each byte that is C
 140          into a zero.  */
 141
 142       longword = *longword_ptr++ ^ charmask;
 143
 144       /* Add MAGIC_BITS to LONGWORD.  */
 145       if ((((longword + magic_bits)
 146
 147             /* Set those bits that were unchanged by the addition.  */
 148             ^ ~longword)
 149
 150            /* Look at only the hole bits.  If any of the hole bits
 151               are unchanged, most likely one of the bytes was a
 152               zero.  */
 153            & ~magic_bits) != 0)
 154         {
 155           /* Which of the bytes was C?  If none of them were, it was
 156              a misfire; continue the search.  */
 157
 158           const unsigned char *cp = (const unsigned char *) (longword_ptr - 1);
 159
 160           if (cp[0] == c)
 161             return (__ptr_t) cp;
 162           if (cp[1] == c)
 163             return (__ptr_t) &cp[1];
 164           if (cp[2] == c)
 165             return (__ptr_t) &cp[2];
 166           if (cp[3] == c)
 167             return (__ptr_t) &cp[3];
 168 #if LONG_MAX > 2147483647
 169           if (cp[4] == c)
 170             return (__ptr_t) &cp[4];
 171           if (cp[5] == c)
 172             return (__ptr_t) &cp[5];
 173           if (cp[6] == c)
 174             return (__ptr_t) &cp[6];
 175           if (cp[7] == c)
 176             return (__ptr_t) &cp[7];
 177 #endif
 178         }
 179     }
 180 }
 181 libc_hidden_def (__rawmemchr)
 182 weak_alias (__rawmemchr, rawmemchr)