memrchr.c 5.9 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197
  1. /* memrchr -- find the last occurrence of a byte in a memory block
  2. Copyright (C) 1991-2019 Free Software Foundation, Inc.
  3. This file is part of the GNU C Library.
  4. Based on strlen implementation by Torbjorn Granlund (tege@sics.se),
  5. with help from Dan Sahlin (dan@sics.se) and
  6. commentary by Jim Blandy (jimb@ai.mit.edu);
  7. adaptation to memchr suggested by Dick Karpinski (dick@cca.ucsf.edu),
  8. and implemented by Roland McGrath (roland@ai.mit.edu).
  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. 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. Lesser General Public License for more details.
  17. You should have received a copy of the GNU Lesser General Public
  18. License along with the GNU C Library; if not, see
  19. <http://www.gnu.org/licenses/>. */
  20. #include <stdlib.h>
  21. #ifdef HAVE_CONFIG_H
  22. # include <config.h>
  23. #endif
  24. #if defined _LIBC
  25. # include <string.h>
  26. # include <memcopy.h>
  27. #endif
  28. #if defined HAVE_LIMITS_H || defined _LIBC
  29. # include <limits.h>
  30. #endif
  31. #define LONG_MAX_32_BITS 2147483647
  32. #ifndef LONG_MAX
  33. # define LONG_MAX LONG_MAX_32_BITS
  34. #endif
  35. #include <sys/types.h>
  36. #undef __memrchr
  37. #undef memrchr
  38. #ifndef weak_alias
  39. # define __memrchr memrchr
  40. #endif
  41. /* Search no more than N bytes of S for C. */
  42. void *
  43. #ifndef MEMRCHR
  44. __memrchr
  45. #else
  46. MEMRCHR
  47. #endif
  48. (const void *s, int c_in, size_t n)
  49. {
  50. const unsigned char *char_ptr;
  51. const unsigned long int *longword_ptr;
  52. unsigned long int longword, magic_bits, charmask;
  53. unsigned char c;
  54. c = (unsigned char) c_in;
  55. /* Handle the last few characters by reading one character at a time.
  56. Do this until CHAR_PTR is aligned on a longword boundary. */
  57. for (char_ptr = (const unsigned char *) s + n;
  58. n > 0 && ((unsigned long int) char_ptr
  59. & (sizeof (longword) - 1)) != 0;
  60. --n)
  61. if (*--char_ptr == c)
  62. return (void *) char_ptr;
  63. /* All these elucidatory comments refer to 4-byte longwords,
  64. but the theory applies equally well to 8-byte longwords. */
  65. longword_ptr = (const unsigned long int *) char_ptr;
  66. /* Bits 31, 24, 16, and 8 of this number are zero. Call these bits
  67. the "holes." Note that there is a hole just to the left of
  68. each byte, with an extra at the end:
  69. bits: 01111110 11111110 11111110 11111111
  70. bytes: AAAAAAAA BBBBBBBB CCCCCCCC DDDDDDDD
  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. magic_bits = -1;
  74. magic_bits = magic_bits / 0xff * 0xfe << 1 >> 1 | 1;
  75. /* Set up a longword, each of whose bytes is C. */
  76. charmask = c | (c << 8);
  77. charmask |= charmask << 16;
  78. #if LONG_MAX > LONG_MAX_32_BITS
  79. charmask |= charmask << 32;
  80. #endif
  81. /* Instead of the traditional loop which tests each character,
  82. we will test a longword at a time. The tricky part is testing
  83. if *any of the four* bytes in the longword in question are zero. */
  84. while (n >= sizeof (longword))
  85. {
  86. /* We tentatively exit the loop if adding MAGIC_BITS to
  87. LONGWORD fails to change any of the hole bits of LONGWORD.
  88. 1) Is this safe? Will it catch all the zero bytes?
  89. Suppose there is a byte with all zeros. Any carry bits
  90. propagating from its left will fall into the hole at its
  91. least significant bit and stop. Since there will be no
  92. carry from its most significant bit, the LSB of the
  93. byte to the left will be unchanged, and the zero will be
  94. detected.
  95. 2) Is this worthwhile? Will it ignore everything except
  96. zero bytes? Suppose every byte of LONGWORD has a bit set
  97. somewhere. There will be a carry into bit 8. If bit 8
  98. is set, this will carry into bit 16. If bit 8 is clear,
  99. one of bits 9-15 must be set, so there will be a carry
  100. into bit 16. Similarly, there will be a carry into bit
  101. 24. If one of bits 24-30 is set, there will be a carry
  102. into bit 31, so all of the hole bits will be changed.
  103. The one misfire occurs when bits 24-30 are clear and bit
  104. 31 is set; in this case, the hole at bit 31 is not
  105. changed. If we had access to the processor carry flag,
  106. we could close this loophole by putting the fourth hole
  107. at bit 32!
  108. So it ignores everything except 128's, when they're aligned
  109. properly.
  110. 3) But wait! Aren't we looking for C, not zero?
  111. Good point. So what we do is XOR LONGWORD with a longword,
  112. each of whose bytes is C. This turns each byte that is C
  113. into a zero. */
  114. longword = *--longword_ptr ^ charmask;
  115. /* Add MAGIC_BITS to LONGWORD. */
  116. if ((((longword + magic_bits)
  117. /* Set those bits that were unchanged by the addition. */
  118. ^ ~longword)
  119. /* Look at only the hole bits. If any of the hole bits
  120. are unchanged, most likely one of the bytes was a
  121. zero. */
  122. & ~magic_bits) != 0)
  123. {
  124. /* Which of the bytes was C? If none of them were, it was
  125. a misfire; continue the search. */
  126. const unsigned char *cp = (const unsigned char *) longword_ptr;
  127. #if LONG_MAX > 2147483647
  128. if (cp[7] == c)
  129. return (void *) &cp[7];
  130. if (cp[6] == c)
  131. return (void *) &cp[6];
  132. if (cp[5] == c)
  133. return (void *) &cp[5];
  134. if (cp[4] == c)
  135. return (void *) &cp[4];
  136. #endif
  137. if (cp[3] == c)
  138. return (void *) &cp[3];
  139. if (cp[2] == c)
  140. return (void *) &cp[2];
  141. if (cp[1] == c)
  142. return (void *) &cp[1];
  143. if (cp[0] == c)
  144. return (void *) cp;
  145. }
  146. n -= sizeof (longword);
  147. }
  148. char_ptr = (const unsigned char *) longword_ptr;
  149. while (n-- > 0)
  150. {
  151. if (*--char_ptr == c)
  152. return (void *) char_ptr;
  153. }
  154. return 0;
  155. }
  156. #ifndef MEMRCHR
  157. # ifdef weak_alias
  158. weak_alias (__memrchr, memrchr)
  159. # endif
  160. #endif