strlen 老瓶裝新酒_ZenDei技術網路在線

前言 - strlen 概述無意間掃到 glibc strlen.c 中代碼, 久久不能忘懷. 在一無所知的編程生涯中又記起點點滴滴: 編程可不是兒戲 ❀, 有些難, 也有些不捨. 隨軌跡一同重溫, 曾經最熟悉的 strlen 手感吧 ~ /* Copyright (C) 1991-2020 Fr ...

前言 - strlen 概述

　　無意間掃到 glibc strlen.c 中代碼, 久久不能忘懷. 在一無所知的編程生涯中又記起點點滴滴:

編程可不是兒戲 ❀, 有些難, 也有些不捨. 隨軌跡一同重溫, 曾經最熟悉的 strlen 手感吧 ~

/* Copyright (C) 1991-2020 Free Software Foundation, Inc.
   This file is part of the GNU C Library.
   Written by Torbjorn Granlund ([email protected]),
   with help from Dan Sahlin ([email protected]);
   commentary by Jim Blandy ([email protected]).

   The GNU C Library is free software; you can redistribute it and/or
   modify it under the terms of the GNU Lesser General Public
   License as published by the Free Software Foundation; either
   version 2.1 of the License, or (at your option) any later version.

   The GNU C Library is distributed in the hope that it will be useful,
   but WITHOUT ANY WARRANTY; without even the implied warranty of
   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
   Lesser General Public License for more details.

   You should have received a copy of the GNU Lesser General Public
   License along with the GNU C Library; if not, see
   <https://www.gnu.org/licenses/>.  */

#include <string.h>
#include <stdlib.h>

#undef strlen

#ifndef STRLEN
# define STRLEN strlen
#endif

/* Return the length of the null-terminated string STR.  Scan for
   the null terminator quickly by testing four bytes at a time.  */
size_t
STRLEN (const char *str)
{
  const char *char_ptr;
  const unsigned long int *longword_ptr;
  unsigned long int longword, himagic, lomagic;

  /* Handle the first few characters by reading one character at a time.
     Do this until CHAR_PTR is aligned on a longword boundary.  */
  for (char_ptr = str; ((unsigned long int) char_ptr
            & (sizeof (longword) - 1)) != 0;
       ++char_ptr)
    if (*char_ptr == '\0')
      return char_ptr - str;

  /* All these elucidatory comments refer to 4-byte longwords,
     but the theory applies equally well to 8-byte longwords.  */

  longword_ptr = (unsigned long int *) char_ptr;

  /* Bits 31, 24, 16, and 8 of this number are zero.  Call these bits
     the "holes."  Note that there is a hole just to the left of
     each byte, with an extra at the end:

     bits:  01111110 11111110 11111110 11111111
     bytes: AAAAAAAA BBBBBBBB CCCCCCCC DDDDDDDD

     The 1-bits make sure that carries propagate to the next 0-bit.
     The 0-bits provide holes for carries to fall into.  */
  himagic = 0x80808080L;
  lomagic = 0x01010101L;
  if (sizeof (longword) > 4)
    {
      /* 64-bit version of the magic.  */
      /* Do the shift in two steps to avoid a warning if long has 32 bits.  */
      himagic = ((himagic << 16) << 16) | himagic;
      lomagic = ((lomagic << 16) << 16) | lomagic;
    }
  if (sizeof (longword) > 8)
    abort ();

  /* Instead of the traditional loop which tests each character,
     we will test a longword at a time.  The tricky part is testing
     if *any of the four* bytes in the longword in question are zero.  */
  for (;;)
    {
      longword = *longword_ptr++;

      if (((longword - lomagic) & ~longword & himagic) != 0)
    {
      /* Which of the bytes was the zero?  If none of them were, it was
         a misfire; continue the search.  */

      const char *cp = (const char *) (longword_ptr - 1);

      if (cp[0] == 0)
        return cp - str;
      
      if (cp[1] == 0)
        return cp - str + 1;
      if (cp[2] == 0)
        return cp - str + 2;
      if (cp[3] == 0)
        return cp - str + 3;
      if (sizeof (longword) > 4)
        {
          if (cp[4] == 0)
        return cp - str + 4;
          if (cp[5] == 0)
        return cp - str + 5;
          if (cp[6] == 0)
        return cp - str + 6;
          if (cp[7] == 0)
        return cp - str + 7;
        }
    }
    }
}
libc_hidden_builtin_def (strlen)

正文 - 思考和分析

1. unsigned long int 位元組多大 4 位元組, 8 位元組 ?

  unsigned long int longword, himagic, lomagic;

long 具體多長和平臺有關, 例如大多數 linux , x86 sizeof (long) = 4, x64 sizeof (long) = 8.

window x86, x64 sizeof (long) = 4. (2020年05月28日), C 標準保證 sizeof(long) >= sizeof (int)

具體多少位元組交給了實現方.

2. ((unsigned long int) char_ptr & (sizeof (longword) - 1)) 位對齊 ?

  /* Handle the first few characters by reading one character at a time.
     Do this until CHAR_PTR is aligned on a longword boundary.  */
  for (char_ptr = str; ((unsigned long int) char_ptr
            & (sizeof (longword) - 1)) != 0;
       ++char_ptr)
    if (*char_ptr == '\0')
      return char_ptr - str;

起始的這些代碼的作用是, 讓 chart_ptr 按照 sizeof (unsigned long) 位元組大小進行位對齊.

這涉及到多數電腦硬體對齊有要求和性能方面的考慮等等(性能是主要因素).

3. himagic = 0x80808080L; lomagic = 0x01010101L; what fuck ?

  /* Bits 31, 24, 16, and 8 of this number are zero.  Call these bits
     the "holes."  Note that there is a hole just to the left of
     each byte, with an extra at the end:

     bits:  01111110 11111110 11111110 11111111
     bytes: AAAAAAAA BBBBBBBB CCCCCCCC DDDDDDDD

     The 1-bits make sure that carries propagate to the next 0-bit.
     The 0-bits provide holes for carries to fall into.  */
  himagic = 0x80808080L;
  lomagic = 0x01010101L;
  if (sizeof (longword) > 4)
    {
      /* 64-bit version of the magic.  */
      /* Do the shift in two steps to avoid a warning if long has 32 bits.  */
      himagic = ((himagic << 16) << 16) | himagic;
      lomagic = ((lomagic << 16) << 16) | lomagic;
    }
  if (sizeof (longword) > 8)
    abort ();

  /* Instead of the traditional loop which tests each character,
     we will test a longword at a time.  The tricky part is testing
     if *any of the four* bytes in the longword in question are zero.  */
  for (;;)
    {
      longword = *longword_ptr++;

      if (((longword - lomagic) & ~longword & himagic) != 0)
    {

3.1 (((longword - lomagic) & ~longword & himagic) != 0) ? mmp ?

可能這就是藝術吧. 想到這個想法的, 真是個天才啊! 好巧妙. 哈哈哈. 我們會分兩個小點說明下.

首次看, 感覺有點萌. 我這裡用個簡單的思路來帶大家理解這個問題. 上面代碼主要圍繞

sizeof (unsigned long) 4 位元組和 8 位元組去處理得到. 我們簡單點, 通過處理 1 位元組, 類比遞歸機制.

搞懂這個公式背後的原理 (ˇˍˇ) ～

/**
 * himagic      : 1000 0000
 * lomagic      : 0000 0001
 * longword     : XXXX XXXX
 * /
unsigned long himagic = 0x80L;
unsigned long lomagic = 0x01L;

unsigned long longword ;

隨後我們仔細分析下麵公式

((longword - lomagic) & ~longword & himagic)

( & himagic ) = ( & 1000 0000) 表明最終只在乎最高位.

longword 分三種情況討論

longword     : 1XXX XXXX  128 =< x <= 255
longword     : 0XXX XXXX  0 < x < 128
longword     : 0000 0000  x = 0

第一種 longword = 1XXX XXXX

那麼 ~longword = 0YYY YYYY 顯然 ~ longword & himagic = 0000 0000 不用繼續了.

第二種 longword = 0XXX XXXX 且不為 0, 及不小於 1

顯然 (longword - lomagic) = 0ZZZ ZZZ >= 0 且 < 127, 因為 lomagic = 1;

此刻 (longword - lomagic) & himagic = 0ZZZ ZZZZ & 1000 0000 = 0 , 所以也不需要繼續了.

第三種 longword = 0000 0000

那麼 ~longword & himagic = 1111 1111 & 1000 0000 = 1000 000;

再看 (longword - lomagic) = (0000 0000 - 0000 0001) , 由於無符號數減法是按照

(補碼(0000 0000) + 補碼(-000 0001)) = (補碼(0000 0000) + 補碼(~000 0001 + 1))

= (補碼(0000 0000) + 補碼(1111 1111)) = 1111 1111 (快捷的可以查公式得到最終結果),

因而此刻最終結果為 1111 1111 & 1000 0000 = 1000 0000 > 0.

綜合討論, 可以根據上面公式巧妙的篩選出值是否為 0. 對於 2位元組, 4 位元組, 8 位元組, 思路完全相似.

3.2 (sizeof (longword) > 4) ? (sizeof (longword) > 8) 為什麼不用巨集, 大展巨集圖唄 ?

巨集可以做到多平臺源碼共用, 無法做到多平臺二進位共用. glibc 這麼通用項目, 可移植性影響因數

可能會很重. (性能是毒酒, 想活的久還是少喝 ~ )

4. libc_hidden_builtin_def (strlen) ? 鬧哪樣 ~

理解這個東西, 要引入些場外信息 (不同編譯參數會不一樣, 這裡只抽取其中一條分支解法)

// file : glibc-2.31/include/libc-symbols.h

libc_hidden_builtin_def (strlen)

#define libc_hidden_builtin_def(name) libc_hidden_def (name)

# define libc_hidden_def(name) hidden_def (name)

/* Define ALIASNAME as a strong alias for NAME.  */
# define strong_alias(name, aliasname) _strong_alias(name, aliasname)
# define _strong_alias(name, aliasname) \
  extern __typeof (name) aliasname __attribute__ ((alias (#name))) \
    __attribute_copy__ (name);

/* For assembly, we need to do the opposite of what we do in C:
   in assembly gcc __REDIRECT stuff is not in place, so functions
   are defined by its normal name and we need to create the
   __GI_* alias to it, in C __REDIRECT causes the function definition
   to use __GI_* name and we need to add alias to the real name.
   There is no reason to use hidden_weak over hidden_def in assembly,
   but we provide it for consistency with the C usage.
   hidden_proto doesn't make sense for assembly but the equivalent
   is to call via the HIDDEN_JUMPTARGET macro instead of JUMPTARGET.  */
#  define hidden_def(name)    strong_alias (name, __GI_##name)

/* Undefine (also defined in libc-symbols.h).  */
#undef __attribute_copy__
#if __GNUC_PREREQ (9, 0)
/* Copies attributes from the declaration or type referenced by
   the argument.  */
# define __attribute_copy__(arg) __attribute__ ((__copy__ (arg)))
#else
# define __attribute_copy__(arg)
#endif

利用上面巨集定義, 進行展開

libc_hidden_builtin_def (strlen)
|

hidden_def (strlen)
|

strong_alias (strlen, __GI_strlen)
|

_strong_alias (strlen, __GI_strlen)
|

extern __typeof (strlen) __GI_strlen __attribute__ ((alias ("strlen"))) __attribute_copy__ (strlen);
|

extern __typeof (strlen) __GI_strlen __attribute__ ((alias ("strlen"))) __attribute__ ((__copy__ (strlen)));
``

其中 GUN C 擴展語法

　　__typeof (arg) : 獲取變數的聲明的類型　　__attribute__ ((__copy__ (arg))) : GCC 9 以上版本 attribute copy 複製特性　　alias_name __attribute__ ((alias (name))) : 為 name 聲明符號別名 alias name. 總結: libc_hidden_builtin_def (strlen) 意思是基於 strlen 符號, 重新定義一個符號別名 __GI_strlen. (補充資料 strong_alias 註釋) strlen 工程代碼有很多種, 我們這裡選擇一個通用 glibc 版本去思考和分析. 有興趣可以自行查閱更多. 隨口就來 ~ 做人嘛開心最重要 ~ 千錘百煉芮成鋼 ~ 哈哈哈

後記 - 展望與生活

　　錯誤是難免的, 歡迎指正和交流 ~