string/strnlen.c

   1 /* Find the length of STRING, but scan at most MAXLEN characters.
   2    Copyright (C) 1991, 1993, 1997, 2000, 2001, 2005, 2011 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
  30 #ifdef STRNLEN
  31 # define __strnlen STRNLEN
  32 #endif
  33
  34 size_t
  35 __strnlen (const char *str, size_t maxlen)
  36 {
  37   const char *char_ptr, *end_ptr = str + maxlen;
  38   const unsigned long int *longword_ptr;
  39   unsigned long int longword, himagic, lomagic;
  40
  41   if (maxlen == 0)
  42     return 0;
  43
  44   if (__builtin_expect (end_ptr < str, 0))
  45     end_ptr = (const char *) ~0UL;
  46
  47   /* Handle the first few characters by reading one character at a time.
  48      Do this until CHAR_PTR is aligned on a longword boundary.  */
  49   for (char_ptr = str; ((unsigned long int) char_ptr
  50                         & (sizeof (longword) - 1)) != 0;
  51        ++char_ptr)
  52     if (*char_ptr == '\0')
  53       {
  54         if (char_ptr > end_ptr)
  55           char_ptr = end_ptr;
  56         return char_ptr - str;
  57       }
  58
  59   /* All these elucidatory comments refer to 4-byte longwords,
  60      but the theory applies equally well to 8-byte longwords.  */
  61
  62   longword_ptr = (unsigned long int *) char_ptr;
  63
  64   /* Bits 31, 24, 16, and 8 of this number are zero.  Call these bits
  65      the "holes."  Note that there is a hole just to the left of
  66      each byte, with an extra at the end:
  67
  68      bits:  01111110 11111110 11111110 11111111
  69      bytes: AAAAAAAA BBBBBBBB CCCCCCCC DDDDDDDD
  70
  71      The 1-bits make sure that carries propagate to the next 0-bit.
  72      The 0-bits provide holes for carries to fall into.  */
  73   himagic = 0x80808080L;
  74   lomagic = 0x01010101L;
  75   if (sizeof (longword) > 4)
  76     {
  77       /* 64-bit version of the magic.  */
  78       /* Do the shift in two steps to avoid a warning if long has 32 bits.  */
  79       himagic = ((himagic << 16) << 16) | himagic;
  80       lomagic = ((lomagic << 16) << 16) | lomagic;
  81     }
  82   if (sizeof (longword) > 8)
  83     abort ();
  84
  85   /* Instead of the traditional loop which tests each character,
  86      we will test a longword at a time.  The tricky part is testing
  87      if *any of the four* bytes in the longword in question are zero.  */
  88   while (longword_ptr < (unsigned long int *) end_ptr)
  89     {
  90       /* We tentatively exit the loop if adding MAGIC_BITS to
  91          LONGWORD fails to change any of the hole bits of LONGWORD.
  92
  93          1) Is this safe?  Will it catch all the zero bytes?
  94          Suppose there is a byte with all zeros.  Any carry bits
  95          propagating from its left will fall into the hole at its
  96          least significant bit and stop.  Since there will be no
  97          carry from its most significant bit, the LSB of the
  98          byte to the left will be unchanged, and the zero will be
  99          detected.
 100
 101          2) Is this worthwhile?  Will it ignore everything except
 102          zero bytes?  Suppose every byte of LONGWORD has a bit set
 103          somewhere.  There will be a carry into bit 8.  If bit 8
 104          is set, this will carry into bit 16.  If bit 8 is clear,
 105          one of bits 9-15 must be set, so there will be a carry
 106          into bit 16.  Similarly, there will be a carry into bit
 107          24.  If one of bits 24-30 is set, there will be a carry
 108          into bit 31, so all of the hole bits will be changed.
 109
 110          The one misfire occurs when bits 24-30 are clear and bit
 111          31 is set; in this case, the hole at bit 31 is not
 112          changed.  If we had access to the processor carry flag,
 113          we could close this loophole by putting the fourth hole
 114          at bit 32!
 115
 116          So it ignores everything except 128's, when they're aligned
 117          properly.  */
 118
 119       longword = *longword_ptr++;
 120
 121       if ((longword - lomagic) & himagic)
 122         {
 123           /* Which of the bytes was the zero?  If none of them were, it was
 124              a misfire; continue the search.  */
 125
 126           const char *cp = (const char *) (longword_ptr - 1);
 127
 128           char_ptr = cp;
 129           if (cp[0] == 0)
 130             break;
 131           char_ptr = cp + 1;
 132           if (cp[1] == 0)
 133             break;
 134           char_ptr = cp + 2;
 135           if (cp[2] == 0)
 136             break;
 137           char_ptr = cp + 3;
 138           if (cp[3] == 0)
 139             break;
 140           if (sizeof (longword) > 4)
 141             {
 142               char_ptr = cp + 4;
 143               if (cp[4] == 0)
 144                 break;
 145               char_ptr = cp + 5;
 146               if (cp[5] == 0)
 147                 break;
 148               char_ptr = cp + 6;
 149               if (cp[6] == 0)
 150                 break;
 151               char_ptr = cp + 7;
 152               if (cp[7] == 0)
 153                 break;
 154             }
 155         }
 156       char_ptr = end_ptr;
 157     }
 158
 159   if (char_ptr > end_ptr)
 160     char_ptr = end_ptr;
 161   return char_ptr - str;
 162 }
 163 #ifndef STRNLEN
 164 weak_alias (__strnlen, strnlen)
 165 #endif
 166 libc_hidden_def (strnlen)