bss section (2)

env: in 32bit linux, 64 bit 似乎有點不同??

在沒有 os 的環境下搞懂 bss 有點麻煩嗎？這次提供在 os 環境下, 看看 bss。
首先找出 bss 開始和結束的地方。先來看看 default linker script。

ld --verbose

 GNU ld (GNU Binutils for Debian) 2.22
   Supported emulations:
    elf_i386
    i386linux
    elf32_x86_64
    elf_x86_64
    elf_l1om
    elf_k1om
 using internal linker script:
 ==================================================
 /* Script for -z combreloc: combine and sort reloc sections */
 OUTPUT_FORMAT("elf32-i386", "elf32-i386",
        "elf32-i386")
 OUTPUT_ARCH(i386)
 ENTRY(_start)
 SEARCH_DIR("/usr/i486-linux-gnu/lib32"); SEARCH_DIR("=/usr/local/lib32"); 

SEARCH_DIR("=/lib32"); SEARCH_DIR("=/usr/lib32"); 

SEARCH_DIR("=/usr/local/lib/i386-linux-gnu"); SEARCH_DIR("=/usr/local/lib"); 

SEARCH_DIR("=/lib/i386-linux-gnu"); SEARCH_DIR("=/lib"); 

SEARCH_DIR("=/usr/lib/i386-linux-gnu"); SEARCH_DIR("=/usr/lib");
 SECTIONS
 {
   /* Read-only sections, merged into text segment: */
   PROVIDE (__executable_start = SEGMENT_START("text-segment", 0x08048000)); 

. = SEGMENT_START("text-segment", 0x08048000) + SIZEOF_HEADERS;
   .interp         : { *(.interp) }
   .note.gnu.build-id : { *(.note.gnu.build-id) }
   .hash           : { *(.hash) }
   .gnu.hash       : { *(.gnu.hash) }
   .dynsym         : { *(.dynsym) }
   .dynstr         : { *(.dynstr) }
   .gnu.version    : { *(.gnu.version) }
   .gnu.version_d  : { *(.gnu.version_d) }
   .gnu.version_r  : { *(.gnu.version_r) }
   .rel.dyn        :
     {
       *(.rel.init)
       *(.rel.text .rel.text.* .rel.gnu.linkonce.t.*)
       *(.rel.fini)
       *(.rel.rodata .rel.rodata.* .rel.gnu.linkonce.r.*)
       *(.rel.data.rel.ro* .rel.gnu.linkonce.d.rel.ro.*)
       *(.rel.data .rel.data.* .rel.gnu.linkonce.d.*)
       *(.rel.tdata .rel.tdata.* .rel.gnu.linkonce.td.*)
       *(.rel.tbss .rel.tbss.* .rel.gnu.linkonce.tb.*)
       *(.rel.ctors)
       *(.rel.dtors)
       *(.rel.got)
       *(.rel.bss .rel.bss.* .rel.gnu.linkonce.b.*)
       *(.rel.ifunc)
     }
   .rel.plt        :
     {
       *(.rel.plt)
       PROVIDE_HIDDEN (__rel_iplt_start = .);
       *(.rel.iplt)
       PROVIDE_HIDDEN (__rel_iplt_end = .);
     }
   .init           :
   {
     KEEP (*(.init))
   } =0x90909090
   .plt            : { *(.plt) *(.iplt) }
   .text           :
   {
     *(.text.unlikely .text.*_unlikely)
     *(.text.exit .text.exit.*)
     *(.text.startup .text.startup.*)
     *(.text.hot .text.hot.*)
     *(.text .stub .text.* .gnu.linkonce.t.*)
     /* .gnu.warning sections are handled specially by elf32.em.  */
     *(.gnu.warning)
   } =0x90909090
   .fini           :
   {
     KEEP (*(.fini))
   } =0x90909090
   PROVIDE (__etext = .);
   PROVIDE (_etext = .);
   PROVIDE (etext = .);
   .rodata         : { *(.rodata .rodata.* .gnu.linkonce.r.*) }
   .rodata1        : { *(.rodata1) }
   .eh_frame_hdr : { *(.eh_frame_hdr) }
   .eh_frame       : ONLY_IF_RO { KEEP (*(.eh_frame)) }
   .gcc_except_table   : ONLY_IF_RO { *(.gcc_except_table
   .gcc_except_table.*) }
   /* These sections are generated by the Sun/Oracle C++ compiler.  */
   .exception_ranges   : ONLY_IF_RO { *(.exception_ranges
   .exception_ranges*) }
   /* Adjust the address for the data segment.  We want to adjust up to
      the same address within the page on the next page up.  */
   . = ALIGN (CONSTANT (MAXPAGESIZE)) - ((CONSTANT (MAXPAGESIZE) - .) 

& (CONSTANT (MAXPAGESIZE) - 1)); 

. = DATA_SEGMENT_ALIGN (CONSTANT (MAXPAGESIZE), CONSTANT (COMMONPAGESIZE));
   /* Exception handling  */
   .eh_frame       : ONLY_IF_RW { KEEP (*(.eh_frame)) }
   .gcc_except_table   : ONLY_IF_RW { *(.gcc_except_table .gcc_except_table.*) }
   .exception_ranges   : ONLY_IF_RW { *(.exception_ranges .exception_ranges*) }
   /* Thread Local Storage sections  */
   .tdata   : { *(.tdata .tdata.* .gnu.linkonce.td.*) }
   .tbss    : { *(.tbss .tbss.* .gnu.linkonce.tb.*) *(.tcommon) }
   .preinit_array     :
   {
     PROVIDE_HIDDEN (__preinit_array_start = .);
     KEEP (*(.preinit_array))
     PROVIDE_HIDDEN (__preinit_array_end = .);
   }
   .init_array     :
   {
     PROVIDE_HIDDEN (__init_array_start = .);
     KEEP (*(SORT_BY_INIT_PRIORITY(.init_array.*) SORT_BY_INIT_PRIORITY(.ctors.*)))
     KEEP (*(.init_array))
     KEEP (*(EXCLUDE_FILE (*crtbegin.o *crtbegin?.o *crtend.o *crtend?.o ) .ctors))
     PROVIDE_HIDDEN (__init_array_end = .);
   }
   .fini_array     :
   {
     PROVIDE_HIDDEN (__fini_array_start = .);
     KEEP (*(SORT_BY_INIT_PRIORITY(.fini_array.*) SORT_BY_INIT_PRIORITY(.dtors.*)))
     KEEP (*(.fini_array))
     KEEP (*(EXCLUDE_FILE (*crtbegin.o *crtbegin?.o *crtend.o *crtend?.o ) .dtors))
     PROVIDE_HIDDEN (__fini_array_end = .);
   }
   .ctors          :
   {
     /* gcc uses crtbegin.o to find the start of
        the constructors, so we make sure it is
        first.  Because this is a wildcard, it
        doesn't matter if the user does not
        actually link against crtbegin.o; the
        linker won't look for a file to match a
        wildcard.  The wildcard also means that it
        doesn't matter which directory crtbegin.o
        is in.  */
     KEEP (*crtbegin.o(.ctors))
     KEEP (*crtbegin?.o(.ctors))
     /* We don't want to include the .ctor section from
        the crtend.o file until after the sorted ctors.
        The .ctor section from the crtend file contains the
        end of ctors marker and it must be last */
     KEEP (*(EXCLUDE_FILE (*crtend.o *crtend?.o ) .ctors))
     KEEP (*(SORT(.ctors.*)))
     KEEP (*(.ctors))
   }
   .dtors          :
   {
     KEEP (*crtbegin.o(.dtors))
     KEEP (*crtbegin?.o(.dtors))
     KEEP (*(EXCLUDE_FILE (*crtend.o *crtend?.o ) .dtors))
     KEEP (*(SORT(.dtors.*)))
     KEEP (*(.dtors))
   }
   .jcr            : { KEEP (*(.jcr)) }
   .data.rel.ro : { *(.data.rel.ro.local* .gnu.linkonce.d.rel.ro.local.*) 

*(.data.rel.ro* .gnu.linkonce.d.rel.ro.*) }
   .dynamic        : { *(.dynamic) }
   .got            : { *(.got) *(.igot) }
   . = DATA_SEGMENT_RELRO_END (12, .);
   .got.plt        : { *(.got.plt)  *(.igot.plt) }
   .data           :
   {
     *(.data .data.* .gnu.linkonce.d.*)
     SORT(CONSTRUCTORS)
   }
   .data1          : { *(.data1) }
   _edata = .; PROVIDE (edata = .);
   __bss_start = .;
   .bss            :
   {
    *(.dynbss)
    *(.bss .bss.* .gnu.linkonce.b.*)
    *(COMMON)
    /* Align here to ensure that the .bss section occupies space up to
       _end.  Align after .bss to ensure correct alignment even if the
       .bss section disappears because there are no input sections.
       FIXME: Why do we need it? When there is no .bss section, we don't
       pad the .data section.  */
    . = ALIGN(. != 0 ? 32 / 8 : 1);
   }
   . = ALIGN(32 / 8);
   . = ALIGN(32 / 8);
   _end = .; PROVIDE (end = .);
   . = DATA_SEGMENT_END (.);
   /* Stabs debugging sections.  */
   .stab          0 : { *(.stab) }
   .stabstr       0 : { *(.stabstr) }
   .stab.excl     0 : { *(.stab.excl) }
   .stab.exclstr  0 : { *(.stab.exclstr) }
   .stab.index    0 : { *(.stab.index) }
   .stab.indexstr 0 : { *(.stab.indexstr) }
   .comment       0 : { *(.comment) }
   /* DWARF debug sections.
      Symbols in the DWARF debugging sections are relative to the beginning
      of the section so we begin them at 0.  */
   /* DWARF 1 */
   .debug          0 : { *(.debug) }
   .line           0 : { *(.line) }
   /* GNU DWARF 1 extensions */
   .debug_srcinfo  0 : { *(.debug_srcinfo) }
   .debug_sfnames  0 : { *(.debug_sfnames) }
   /* DWARF 1.1 and DWARF 2 */
   .debug_aranges  0 : { *(.debug_aranges) }
   .debug_pubnames 0 : { *(.debug_pubnames) }
   /* DWARF 2 */
   .debug_info     0 : { *(.debug_info .gnu.linkonce.wi.*) }
   .debug_abbrev   0 : { *(.debug_abbrev) }
   .debug_line     0 : { *(.debug_line) }
   .debug_frame    0 : { *(.debug_frame) }
   .debug_str      0 : { *(.debug_str) }
   .debug_loc      0 : { *(.debug_loc) }
   .debug_macinfo  0 : { *(.debug_macinfo) }
   /* SGI/MIPS DWARF 2 extensions */
   .debug_weaknames 0 : { *(.debug_weaknames) }
   .debug_funcnames 0 : { *(.debug_funcnames) }
   .debug_typenames 0 : { *(.debug_typenames) }
   .debug_varnames  0 : { *(.debug_varnames) }
   /* DWARF 3 */
   .debug_pubtypes 0 : { *(.debug_pubtypes) }
   .debug_ranges   0 : { *(.debug_ranges) }
   .gnu.attributes 0 : { KEEP (*(.gnu.attributes)) }
   /DISCARD/ : { *(.note.GNU-stack) *(.gnu_debuglink) *(.gnu.lto_*) }
 }
 
 
 ==================================================

我知道很長, 我和你一樣大部份有看沒有懂, 只看 L158 ~ L173 就好。

   __bss_start = .;
   .bss            :
   {
    *(.dynbss)
    *(.bss .bss.* .gnu.linkonce.b.*)
    *(COMMON)
    /* Align here to ensure that the .bss section occupies space up to
       _end.  Align after .bss to ensure correct alignment even if the
       .bss section disappears because there are no input sections.
       FIXME: Why do we need it? When there is no .bss section, we don't
       pad the .data section.  */
    . = ALIGN(. != 0 ? 32 / 8 : 1);
   }
   . = ALIGN(32 / 8);
   . = ALIGN(32 / 8);
   _end = .; PROVIDE (end = .);

_end, __bss_start 這兩個 symbol 就是 bss section 的開始和結束。先來看看程式執行結果。

i: 0x8049734
i: 0x8049738
&__bss_start: 0x8049734
&_end: 0x804973c
ABCDEF: 11223344

bss 從  0x8049734 ~ 0x804973c 佔了 8 byte。

ABCDEF 不是預期的 0。表示成功改變 bss 這個區域。這應該簡單多了, 而且也可以馬上在 linux 上實驗。

b.c

 #include <stdio.h>
 
 int ABCDEF;
 extern int _end;
 extern int __bss_start;
 
 void fill_bss(void)
 {
   int *i=0;
   for (i = &__bss_start ; i != &_end ; ++i)
   {
     printf("i: %p\n", i);
     *i = 0x11223344;
   }
 
 }
 
 int main(void)
 {
   fill_bss();
   printf("&__bss_start: %p\n", &__bss_start);
   printf("&_end: %p\n", &_end);
   printf("ABCDEF: %x\n", ABCDEF);
   return 0;
 }

看看 elf 裡頭的資訊:

[26] .bss NOBITS 08049734 000734 000008 00  WA  0   0  4
63: 08049738     4 OBJECT  GLOBAL DEFAULT   26 ABCDEF

bss 佔 8 byte, ABCDEF 則位於 0x08049738

source code:
git clone git@github.com:descent/progs.git'
cd bss

ref:
linux kernel 完全剖析 (3.5.4 p 96)