Erlang源码汇编格式

转：http://blog.yufeng.info/archives/498

我们在编码的时候, 通常会好奇, 这时候需要观察erl源码生成的VM opcode. Erlang的VM是register based的VM, 生产的opcode很容易理解.
生成汇编格式有2种方式:
1. 从源码生成抽象码. erlc +”‘S’” mod.erl, 生成mod.S
2. 从beam生成Opcode. 未公开的功能. erts_debug:df 参数M或者 M, F, 生成mod.dis

来吧,实践下:

root@ubuntu:~/exam# ls

eg.erl

root@ubuntu:~/exam# erlc +"'S'" eg.erl

root@ubuntu:~/exam# erlc eg.erl

root@ubuntu:~/exam# erl

Erlang R14A (erts-5.8) 1 [smp:2:2] [rq:2] [async-threads:0] [hipe] [kernel-poll:false] [lock-counting]

Eshell V5.8  (abort with ^G)

1>  erts_debug:df(eg).

ok

2>

User switch command

 --> q

root@ubuntu:~/exam# ls eg*

eg.beam  eg.dis  eg.erl  eg.S

我们得到了eg.S, eg.dis这2个反汇编的结果. 我们再来参观下.
先看源码:
root@ubuntu:~/exam# cat eg.erl

-module(eg).

-import(lists).

-import(lists,[sum/1]).

-compile(export_all).

kilo_byte() ->

    kilo_byte(10, [42]).

kilo_byte(0, Acc) ->

    Acc;

kilo_byte(N, Acc) ->

    kilo_byte(N-1, [Acc|Acc]).

loop()->

    sum(lists:seq(1,100)),

    loop().

中间汇编码, 供transform进行处理和编译器进一步生成opcode.
root@ubuntu:~/exam# cat eg.S

{module, eg}.  %% version = 0

{exports, [{kilo_byte,0},

           {kilo_byte,2},

           {loop,0},

           {module_info,0},

           {module_info,1}]}.

{attributes, []}.

{labels, 12}.

{function, kilo_byte, 0, 2}.

  {label,1}.

    {func_info,{atom,eg},{atom,kilo_byte},0}.

  {label,2}.

    {move,{literal,"*"},{x,1}}.

    {move,{integer,10},{x,0}}.

    {call_only,2,{f,4}}.

{function, kilo_byte, 2, 4}.

  {label,3}.

    {func_info,{atom,eg},{atom,kilo_byte},2}.

  {label,4}.

    {test,is_eq_exact,{f,5},[{x,0},{integer,0}]}.

    {move,{x,1},{x,0}}.

    return.

  {label,5}.

    {gc_bif,'-',{f,0},2,[{x,0},{integer,1}],{x,0}}.

    {test_heap,2,2}.

    {put_list,{x,1},{x,1},{x,1}}.

    {call_only,2,{f,4}}.

{function, loop, 0, 7}.

  {label,6}.

    {func_info,{atom,eg},{atom,loop},0}.

  {label,7}.

    {allocate,0,0}.

    {move,{integer,100},{x,1}}.

    {move,{integer,1},{x,0}}.

    {call_ext,2,{extfunc,lists,seq,2}}.

    {call_ext,1,{extfunc,lists,sum,1}}.

    {call_last,0,{f,7},0}.

{function, module_info, 0, 9}.

  {label,8}.

    {func_info,{atom,eg},{atom,module_info},0}.

  {label,9}.

    {move,{atom,eg},{x,0}}.

    {call_ext_only,1,{extfunc,erlang,get_module_info,1}}.

{function, module_info, 1, 11}.

  {label,10}.

    {func_info,{atom,eg},{atom,module_info},1}.

  {label,11}.

    {move,{x,0},{x,1}}.

    {move,{atom,eg},{x,0}}.

    {call_ext_only,2,{extfunc,erlang,get_module_info,2}}.

VM opcode形式, VM就是来解释运行这些code的

view source

print?

root@ubuntu:~/exam# cat eg.dis

B5146074: i_func_info_IaaI 0 eg kilo_byte 0

B5146088: move_cx "*" x(1)

B5146094: i_move_call_only_fcr eg:kilo_byte/2 10 x(0)

B51460A0: i_func_info_IaaI 0 eg kilo_byte 2

B51460B4: i_is_eq_immed_frc f(B51460C8) x(0) 0

B51460C0: move_return_xr x(1) x(0)

B51460C8: i_fetch_rc x(0) 1

B51460D0: i_minus_jId j(00000000) 2 x(0)

B51460E0: test_heap_II 2 2

B51460EC: put_list_xxx x(1) x(1) x(1)

B51460F4: i_call_only_f eg:kilo_byte/2

B51460FC: i_func_info_IaaI 0 eg loop 0

B5146110: allocate_tt 0 0

B5146118: move_cx 100 x(1)

B5146124: i_move_call_ext_cre 1 x(0) lists:seq/2

B5146130: i_call_ext_e lists:sum/1

B5146138: i_call_last_fP eg:loop/0 0

B5146144: i_func_info_IaaI 0 eg module_info 0

B5146158: move_cr eg x(0)

B5146160: allocate_tt 0 1

B5146168: call_bif1_e erlang:get_module_info/1

B5146170: deallocate_return_P 0

B5146178: i_func_info_IaaI 0 eg module_info 1

B514618C: move_rx x(0) x(1)

B5146194: move_cr eg x(0)

B514619C: allocate_tt 0 2

B51461A4: call_bif2_e erlang:get_module_info/2

B51461AC: deallocate_return_P 0

收工!