src/string/generic/strlen.c

   1 /*-
   2  * Copyright (c) 2009 Xin LI <delphij@FreeBSD.org>
   3  * All rights reserved.
   4  *
   5  * Redistribution and use in source and binary forms, with or without
   6  * modification, are permitted provided that the following conditions
   7  * are met:
   8  * 1. Redistributions of source code must retain the above copyright
   9  *    notice, this list of conditions and the following disclaimer.
  10  * 2. Redistributions in binary form must reproduce the above copyright
  11  *    notice, this list of conditions and the following disclaimer in the
  12  *    documentation and/or other materials provided with the distribution.
  13  *
  14  * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
  15  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  16  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  17  * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
  18  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  19  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
  20  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
  21  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  22  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
  23  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  24  * SUCH DAMAGE.
  25  */
  26
  27 #include <sys/cdefs.h>
  28 __FBSDID("$FreeBSD: src/lib/libc/string/strlen.c,v 1.7 2009/01/26 07:31:28 delphij Exp $");
  29
  30 #include <limits.h>
  31 #include <sys/types.h>
  32 #include <platform/string.h>
  33
  34 #if !_PLATFORM_OPTIMIZED_STRLEN
  35
  36 /*
  37  * Portable strlen() for 32-bit and 64-bit systems.
  38  *
  39  * Rationale: it is generally much more efficient to do word length
  40  * operations and avoid branches on modern computer systems, as
  41  * compared to byte-length operations with a lot of branches.
  42  *
  43  * The expression:
  44  *
  45  *      ((x - 0x01....01) & ~x & 0x80....80)
  46  *
  47  * would evaluate to a non-zero value iff any of the bytes in the
  48  * original word is zero.  However, we can further reduce ~1/3 of
  49  * time if we consider that strlen() usually operate on 7-bit ASCII
  50  * by employing the following expression, which allows false positive
  51  * when high bit of 1 and use the tail case to catch these case:
  52  *
  53  *      ((x - 0x01....01) & 0x80....80)
  54  *
  55  * This is more than 5.2 times as fast as the raw implementation on
  56  * Intel T7300 under long mode for strings longer than word length.
  57  */
  58
  59 /* Magic numbers for the algorithm */
  60 #if LONG_BIT == 32
  61 static const unsigned long mask01 = 0x01010101;
  62 static const unsigned long mask80 = 0x80808080;
  63 #elif LONG_BIT == 64
  64 static const unsigned long mask01 = 0x0101010101010101;
  65 static const unsigned long mask80 = 0x8080808080808080;
  66 #else
  67 #error Unsupported word size
  68 #endif
  69
  70 #define LONGPTR_MASK (sizeof(long) - 1)
  71
  72 /*
  73  * Helper macro to return string length if we caught the zero
  74  * byte.
  75  */
  76 #define testbyte(x)                             \
  77         do {                                    \
  78                 if (p[x] == '\0')               \
  79                     return (p - str + x);       \
  80         } while (0)
  81
  82 size_t
  83 _platform_strlen(const char *str)
  84 {
  85         const char *p;
  86         const unsigned long *lp;
  87
  88         /* Skip the first few bytes until we have an aligned p */
  89         for (p = str; (uintptr_t)p & LONGPTR_MASK; p++)
  90             if (*p == '\0')
  91                 return (p - str);
  92
  93         /* Scan the rest of the string using word sized operation */
  94         for (lp = (const unsigned long *)p; ; lp++)
  95             if ((*lp - mask01) & mask80) {
  96                 p = (const char *)(lp);
  97                 testbyte(0);
  98                 testbyte(1);
  99                 testbyte(2);
 100                 testbyte(3);
 101 #if (LONG_BIT >= 64)
 102                 testbyte(4);
 103                 testbyte(5);
 104                 testbyte(6);
 105                 testbyte(7);
 106 #endif
 107             }
 108
 109         /* NOTREACHED */
 110         return (0);
 111 }
 112
 113 #if VARIANT_STATIC
 114 size_t
 115 strlen(const char *str)
 116 {
 117         return _platform_strlen(str);
 118 }
 119 #endif
 120
 121 #endif
 122