string/strnlen.c

   1 /* Find the length of STRING, but scan at most MAXLEN characters.
   2    Copyright (C) 1991,1993,1997,2000,2001,2005 Free Software Foundation, Inc.
   3    Contributed by Jakub Jelinek <jakub@redhat.com>.
   4
   5    Based on strlen written by Torbjorn Granlund (tege@sics.se),
   6    with help from Dan Sahlin (dan@sics.se);
   7    commentary by Jim Blandy (jimb@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 License as
  11    published by the Free Software Foundation; either version 2.1 of the
  12    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; see the file COPYING.LIB.  If not,
  21    write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
  22    Boston, MA 02111-1307, USA.  */
  23
  24 #include <string.h>
  25 #include <stdlib.h>
  26
  27 /* Find the length of S, but scan at most MAXLEN characters.  If no
  28    '\0' terminator is found in that many characters, return MAXLEN.  */
  29 size_t
  30 __strnlen (const char *str, size_t maxlen)
  31 {
  32   const char *char_ptr, *end_ptr = str + maxlen;
  33   const unsigned long int *longword_ptr;
  34   unsigned long int longword, magic_bits, himagic, lomagic;
  35
  36   if (maxlen == 0)
  37     return 0;
  38
  39   if (__builtin_expect (end_ptr < str, 0))
  40     end_ptr = (const char *) ~0UL;
  41
  42   /* Handle the first few characters by reading one character at a time.
  43      Do this until CHAR_PTR is aligned on a longword boundary.  */
  44   for (char_ptr = str; ((unsigned long int) char_ptr
  45                         & (sizeof (longword) - 1)) != 0;
  46        ++char_ptr)
  47     if (*char_ptr == '\0')
  48       {
  49         if (char_ptr > end_ptr)
  50           char_ptr = end_ptr;
  51         return char_ptr - str;
  52       }
  53
  54   /* All these elucidatory comments refer to 4-byte longwords,
  55      but the theory applies equally well to 8-byte longwords.  */
  56
  57   longword_ptr = (unsigned long int *) char_ptr;
  58
  59   /* Bits 31, 24, 16, and 8 of this number are zero.  Call these bits
  60      the "holes."  Note that there is a hole just to the left of
  61      each byte, with an extra at the end:
  62
  63      bits:  01111110 11111110 11111110 11111111
  64      bytes: AAAAAAAA BBBBBBBB CCCCCCCC DDDDDDDD
  65
  66      The 1-bits make sure that carries propagate to the next 0-bit.
  67      The 0-bits provide holes for carries to fall into.  */
  68   magic_bits = 0x7efefeffL;
  69   himagic = 0x80808080L;
  70   lomagic = 0x01010101L;
  71   if (sizeof (longword) > 4)
  72     {
  73       /* 64-bit version of the magic.  */
  74       /* Do the shift in two steps to avoid a warning if long has 32 bits.  */
  75       magic_bits = ((0x7efefefeL << 16) << 16) | 0xfefefeffL;
  76       himagic = ((himagic << 16) << 16) | himagic;
  77       lomagic = ((lomagic << 16) << 16) | lomagic;
  78     }
  79   if (sizeof (longword) > 8)
  80     abort ();
  81
  82   /* Instead of the traditional loop which tests each character,
  83      we will test a longword at a time.  The tricky part is testing
  84      if *any of the four* bytes in the longword in question are zero.  */
  85   while (longword_ptr < (unsigned long int *) end_ptr)
  86     {
  87       /* We tentatively exit the loop if adding MAGIC_BITS to
  88          LONGWORD fails to change any of the hole bits of LONGWORD.
  89
  90          1) Is this safe?  Will it catch all the zero bytes?
  91          Suppose there is a byte with all zeros.  Any carry bits
  92          propagating from its left will fall into the hole at its
  93          least significant bit and stop.  Since there will be no
  94          carry from its most significant bit, the LSB of the
  95          byte to the left will be unchanged, and the zero will be
  96          detected.
  97
  98          2) Is this worthwhile?  Will it ignore everything except
  99          zero bytes?  Suppose every byte of LONGWORD has a bit set
 100          somewhere.  There will be a carry into bit 8.  If bit 8
 101          is set, this will carry into bit 16.  If bit 8 is clear,
 102          one of bits 9-15 must be set, so there will be a carry
 103          into bit 16.  Similarly, there will be a carry into bit
 104          24.  If one of bits 24-30 is set, there will be a carry
 105          into bit 31, so all of the hole bits will be changed.
 106
 107          The one misfire occurs when bits 24-30 are clear and bit
 108          31 is set; in this case, the hole at bit 31 is not
 109          changed.  If we had access to the processor carry flag,
 110          we could close this loophole by putting the fourth hole
 111          at bit 32!
 112
 113          So it ignores everything except 128's, when they're aligned
 114          properly.  */
 115
 116       longword = *longword_ptr++;
 117
 118       if ((longword - lomagic) & himagic)
 119         {
 120           /* Which of the bytes was the zero?  If none of them were, it was
 121              a misfire; continue the search.  */
 122
 123           const char *cp = (const char *) (longword_ptr - 1);
 124
 125           char_ptr = cp;
 126           if (cp[0] == 0)
 127             break;
 128           char_ptr = cp + 1;
 129           if (cp[1] == 0)
 130             break;
 131           char_ptr = cp + 2;
 132           if (cp[2] == 0)
 133             break;
 134           char_ptr = cp + 3;
 135           if (cp[3] == 0)
 136             break;
 137           if (sizeof (longword) > 4)
 138             {
 139               char_ptr = cp + 4;
 140               if (cp[4] == 0)
 141                 break;
 142               char_ptr = cp + 5;
 143               if (cp[5] == 0)
 144                 break;
 145               char_ptr = cp + 6;
 146               if (cp[6] == 0)
 147                 break;
 148               char_ptr = cp + 7;
 149               if (cp[7] == 0)
 150                 break;
 151             }
 152         }
 153       char_ptr = end_ptr;
 154     }
 155
 156   if (char_ptr > end_ptr)
 157     char_ptr = end_ptr;
 158   return char_ptr - str;
 159 }
 160 weak_alias (__strnlen, strnlen)
 161 libc_hidden_def (strnlen)