string/strnlen.c

   1 /* Find the length of STRING, but scan at most MAXLEN characters.
   2    Copyright (C) 1991-2017 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
  21    not, see <http://www.gnu.org/licenses/>.  */
  22
  23 #include <string.h>
  24 #include <stdlib.h>
  25
  26 /* Find the length of S, but scan at most MAXLEN characters.  If no
  27    '\0' terminator is found in that many characters, return MAXLEN.  */
  28
  29 #ifdef STRNLEN
  30 # define __strnlen STRNLEN
  31 #endif
  32
  33 size_t
  34 __strnlen (const char *str, size_t maxlen)
  35 {
  36   const char *char_ptr, *end_ptr = str + maxlen;
  37   const unsigned long int *longword_ptr;
  38   unsigned long int longword, himagic, lomagic;
  39
  40   if (maxlen == 0)
  41     return 0;
  42
  43   if (__glibc_unlikely (end_ptr < str))
  44     end_ptr = (const char *) ~0UL;
  45
  46   /* Handle the first few characters by reading one character at a time.
  47      Do this until CHAR_PTR is aligned on a longword boundary.  */
  48   for (char_ptr = str; ((unsigned long int) char_ptr
  49                         & (sizeof (longword) - 1)) != 0;
  50        ++char_ptr)
  51     if (*char_ptr == '\0')
  52       {
  53         if (char_ptr > end_ptr)
  54           char_ptr = end_ptr;
  55         return char_ptr - str;
  56       }
  57
  58   /* All these elucidatory comments refer to 4-byte longwords,
  59      but the theory applies equally well to 8-byte longwords.  */
  60
  61   longword_ptr = (unsigned long int *) char_ptr;
  62
  63   /* Bits 31, 24, 16, and 8 of this number are zero.  Call these bits
  64      the "holes."  Note that there is a hole just to the left of
  65      each byte, with an extra at the end:
  66
  67      bits:  01111110 11111110 11111110 11111111
  68      bytes: AAAAAAAA BBBBBBBB CCCCCCCC DDDDDDDD
  69
  70      The 1-bits make sure that carries propagate to the next 0-bit.
  71      The 0-bits provide holes for carries to fall into.  */
  72   himagic = 0x80808080L;
  73   lomagic = 0x01010101L;
  74   if (sizeof (longword) > 4)
  75     {
  76       /* 64-bit version of the magic.  */
  77       /* Do the shift in two steps to avoid a warning if long has 32 bits.  */
  78       himagic = ((himagic << 16) << 16) | himagic;
  79       lomagic = ((lomagic << 16) << 16) | lomagic;
  80     }
  81   if (sizeof (longword) > 8)
  82     abort ();
  83
  84   /* Instead of the traditional loop which tests each character,
  85      we will test a longword at a time.  The tricky part is testing
  86      if *any of the four* bytes in the longword in question are zero.  */
  87   while (longword_ptr < (unsigned long int *) end_ptr)
  88     {
  89       /* We tentatively exit the loop if adding MAGIC_BITS to
  90          LONGWORD fails to change any of the hole bits of LONGWORD.
  91
  92          1) Is this safe?  Will it catch all the zero bytes?
  93          Suppose there is a byte with all zeros.  Any carry bits
  94          propagating from its left will fall into the hole at its
  95          least significant bit and stop.  Since there will be no
  96          carry from its most significant bit, the LSB of the
  97          byte to the left will be unchanged, and the zero will be
  98          detected.
  99
 100          2) Is this worthwhile?  Will it ignore everything except
 101          zero bytes?  Suppose every byte of LONGWORD has a bit set
 102          somewhere.  There will be a carry into bit 8.  If bit 8
 103          is set, this will carry into bit 16.  If bit 8 is clear,
 104          one of bits 9-15 must be set, so there will be a carry
 105          into bit 16.  Similarly, there will be a carry into bit
 106          24.  If one of bits 24-30 is set, there will be a carry
 107          into bit 31, so all of the hole bits will be changed.
 108
 109          The one misfire occurs when bits 24-30 are clear and bit
 110          31 is set; in this case, the hole at bit 31 is not
 111          changed.  If we had access to the processor carry flag,
 112          we could close this loophole by putting the fourth hole
 113          at bit 32!
 114
 115          So it ignores everything except 128's, when they're aligned
 116          properly.  */
 117
 118       longword = *longword_ptr++;
 119
 120       if ((longword - lomagic) & himagic)
 121         {
 122           /* Which of the bytes was the zero?  If none of them were, it was
 123              a misfire; continue the search.  */
 124
 125           const char *cp = (const char *) (longword_ptr - 1);
 126
 127           char_ptr = cp;
 128           if (cp[0] == 0)
 129             break;
 130           char_ptr = cp + 1;
 131           if (cp[1] == 0)
 132             break;
 133           char_ptr = cp + 2;
 134           if (cp[2] == 0)
 135             break;
 136           char_ptr = cp + 3;
 137           if (cp[3] == 0)
 138             break;
 139           if (sizeof (longword) > 4)
 140             {
 141               char_ptr = cp + 4;
 142               if (cp[4] == 0)
 143                 break;
 144               char_ptr = cp + 5;
 145               if (cp[5] == 0)
 146                 break;
 147               char_ptr = cp + 6;
 148               if (cp[6] == 0)
 149                 break;
 150               char_ptr = cp + 7;
 151               if (cp[7] == 0)
 152                 break;
 153             }
 154         }
 155       char_ptr = end_ptr;
 156     }
 157
 158   if (char_ptr > end_ptr)
 159     char_ptr = end_ptr;
 160   return char_ptr - str;
 161 }
 162 #ifndef STRNLEN
 163 libc_hidden_def (__strnlen)
 164 weak_alias (__strnlen, strnlen)
 165 #endif
 166 libc_hidden_def (strnlen)