sysdeps/generic/memchr.c

   1 /* Copyright (C) 1991, 1993 Free Software Foundation, Inc.
   2    Based on strlen implemention by Torbjorn Granlund (tege@sics.se),
   3    with help from Dan Sahlin (dan@sics.se) and
   4    commentary by Jim Blandy (jimb@ai.mit.edu);
   5    adaptation to memchr suggested by Dick Karpinski (dick@cca.ucsf.edu),
   6    and implemented by Roland McGrath (roland@ai.mit.edu).
   7
   8 The GNU C Library is free software; you can redistribute it and/or
   9 modify it under the terms of the GNU Library General Public License as
  10 published by the Free Software Foundation; either version 2 of the
  11 License, or (at your option) any later version.
  12
  13 The GNU C Library is distributed in the hope that it will be useful,
  14 but WITHOUT ANY WARRANTY; without even the implied warranty of
  15 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  16 Library General Public License for more details.
  17
  18 You should have received a copy of the GNU Library General Public
  19 License along with the GNU C Library; see the file COPYING.LIB.  If
  20 not, write to the Free Software Foundation, Inc., 675 Mass Ave,
  21 Cambridge, MA 02139, USA.  */
  22
  23 #ifdef HAVE_CONFIG_H
  24 #include <config.h>
  25 #endif
  26
  27 #undef __ptr_t
  28 #if defined (__cplusplus) || (defined (__STDC__) && __STDC__)
  29 # define __ptr_t void *
  30 #else /* Not C++ or ANSI C.  */
  31 # define __ptr_t char *
  32 #endif /* C++ or ANSI C.  */
  33
  34 #if defined (_LIBC)
  35 # include <string.h>
  36 #endif
  37
  38 #if defined (HAVE_LIMITS_H) || defined (_LIBC)
  39 # include <limits.h>
  40 #endif
  41
  42 #define LONG_MAX_32_BITS 2147483647
  43
  44 #ifndef LONG_MAX
  45 #define LONG_MAX LONG_MAX_32_BITS
  46 #endif
  47
  48 #include <sys/types.h>
  49
  50
  51 /* Search no more than N bytes of S for C.  */
  52
  53 __ptr_t
  54 memchr (s, c, n)
  55      const __ptr_t s;
  56      int c;
  57      size_t n;
  58 {
  59   const unsigned char *char_ptr;
  60   const unsigned long int *longword_ptr;
  61   unsigned long int longword, magic_bits, charmask;
  62
  63   c = (unsigned char) c;
  64
  65   /* Handle the first few characters by reading one character at a time.
  66      Do this until CHAR_PTR is aligned on a longword boundary.  */
  67   for (char_ptr = s; n > 0 && ((unsigned long int) char_ptr
  68                                & (sizeof (longword) - 1)) != 0;
  69        --n, ++char_ptr)
  70     if (*char_ptr == c)
  71       return (__ptr_t) char_ptr;
  72
  73   /* All these elucidatory comments refer to 4-byte longwords,
  74      but the theory applies equally well to 8-byte longwords.  */
  75
  76   longword_ptr = (unsigned long int *) char_ptr;
  77
  78   /* Bits 31, 24, 16, and 8 of this number are zero.  Call these bits
  79      the "holes."  Note that there is a hole just to the left of
  80      each byte, with an extra at the end:
  81
  82      bits:  01111110 11111110 11111110 11111111
  83      bytes: AAAAAAAA BBBBBBBB CCCCCCCC DDDDDDDD
  84
  85      The 1-bits make sure that carries propagate to the next 0-bit.
  86      The 0-bits provide holes for carries to fall into.  */
  87
  88   if (sizeof (longword) != 4 && sizeof (longword) != 8)
  89     abort ();
  90
  91 #if LONG_MAX <= LONG_MAX_32_BITS
  92   magic_bits = 0x7efefeff;
  93 #else
  94   magic_bits = ((unsigned long int) 0x7efefefe << 32) | 0xfefefeff;
  95 #endif
  96
  97   /* Set up a longword, each of whose bytes is C.  */
  98   charmask = c | (c << 8);
  99   charmask |= charmask << 16;
 100 #if LONG_MAX > LONG_MAX_32_BITS
 101   charmask |= charmask << 32;
 102 #endif
 103
 104   /* Instead of the traditional loop which tests each character,
 105      we will test a longword at a time.  The tricky part is testing
 106      if *any of the four* bytes in the longword in question are zero.  */
 107   while (n >= sizeof (longword))
 108     {
 109       /* We tentatively exit the loop if adding MAGIC_BITS to
 110          LONGWORD fails to change any of the hole bits of LONGWORD.
 111
 112          1) Is this safe?  Will it catch all the zero bytes?
 113          Suppose there is a byte with all zeros.  Any carry bits
 114          propagating from its left will fall into the hole at its
 115          least significant bit and stop.  Since there will be no
 116          carry from its most significant bit, the LSB of the
 117          byte to the left will be unchanged, and the zero will be
 118          detected.
 119
 120          2) Is this worthwhile?  Will it ignore everything except
 121          zero bytes?  Suppose every byte of LONGWORD has a bit set
 122          somewhere.  There will be a carry into bit 8.  If bit 8
 123          is set, this will carry into bit 16.  If bit 8 is clear,
 124          one of bits 9-15 must be set, so there will be a carry
 125          into bit 16.  Similarly, there will be a carry into bit
 126          24.  If one of bits 24-30 is set, there will be a carry
 127          into bit 31, so all of the hole bits will be changed.
 128
 129          The one misfire occurs when bits 24-30 are clear and bit
 130          31 is set; in this case, the hole at bit 31 is not
 131          changed.  If we had access to the processor carry flag,
 132          we could close this loophole by putting the fourth hole
 133          at bit 32!
 134
 135          So it ignores everything except 128's, when they're aligned
 136          properly.
 137
 138          3) But wait!  Aren't we looking for C, not zero?
 139          Good point.  So what we do is XOR LONGWORD with a longword,
 140          each of whose bytes is C.  This turns each byte that is C
 141          into a zero.  */
 142
 143       longword = *longword_ptr++ ^ charmask;
 144
 145       /* Add MAGIC_BITS to LONGWORD.  */
 146       if ((((longword + magic_bits)
 147
 148             /* Set those bits that were unchanged by the addition.  */
 149             ^ ~longword)
 150
 151            /* Look at only the hole bits.  If any of the hole bits
 152               are unchanged, most likely one of the bytes was a
 153               zero.  */
 154            & ~magic_bits) != 0)
 155         {
 156           /* Which of the bytes was C?  If none of them were, it was
 157              a misfire; continue the search.  */
 158
 159           const unsigned char *cp = (const unsigned char *) (longword_ptr - 1);
 160
 161           if (cp[0] == c)
 162             return (__ptr_t) cp;
 163           if (cp[1] == c)
 164             return (__ptr_t) &cp[1];
 165           if (cp[2] == c)
 166             return (__ptr_t) &cp[2];
 167           if (cp[3] == c)
 168             return (__ptr_t) &cp[3];
 169 #if LONG_MAX > 2147483647
 170           if (cp[4] == c)
 171             return (__ptr_t) &cp[4];
 172           if (cp[5] == c)
 173             return (__ptr_t) &cp[5];
 174           if (cp[6] == c)
 175             return (__ptr_t) &cp[6];
 176           if (cp[7] == c)
 177             return (__ptr_t) &cp[7];
 178 #endif
 179         }
 180
 181       n -= sizeof (longword);
 182     }
 183
 184   char_ptr = (const unsigned char *) longword_ptr;
 185
 186   while (n-- > 0)
 187     {
 188       if (*char_ptr == c)
 189         return (__ptr_t) char_ptr;
 190       else
 191         ++char_ptr;
 192     }
 193
 194   return 0;
 195 }