智能合约从入门到精通：Solidity汇编语言

标签：情况下   变量   制表符   intro   lock   height   blog   根据   嵌套   

contract C {
  function f(uint x) returns (uint y) {
    y = 1;
    for (uint i = 0; i < x; i++)
      y = 2 * y;
  }
}

它将生成下述的汇编内容：

{
  mstore(0x40, 0x60) // store the "free memory pointer"
  // function dispatcher
  switch div(calldataload(0), exp(2, 226))
  case 0xb3de648b {
    let (r) = f(calldataload(4))
    let ret := $allocate(0x20)
    mstore(ret, r)
    return(ret, 0x20)
  }
  default { revert(0, 0) }
  // memory allocator
  function $allocate(size) -> pos {
    pos := mload(0x40)
    mstore(0x40, add(pos, size))
  }
  // the contract function
  function f(x) -> y {
    y := 1
    for { let i := 0 } lt(i, x) { i := add(i, 1) } {
      y := mul(2, y)
    }
  }
}

在经过脱机汇编阶段，它会编译成下述的内容：

{
  mstore(0x40, 0x60)
  {
    let $0 := div(calldataload(0), exp(2, 226))
    jumpi($case1, eq($0, 0xb3de648b))
    jump($caseDefault)
    $case1:
    {
      // the function call - we put return label and arguments on the stack
      $ret1 calldataload(4) jump(f)
      // This is unreachable code. Opcodes are added that mirror the
      // effect of the function on the stack height: Arguments are
      // removed and return values are introduced.
      pop pop
      let r := 0
      $ret1: // the actual return point
      $ret2 0x20 jump($allocate)
      pop pop let ret := 0
      $ret2:
      mstore(ret, r)
      return(ret, 0x20)
      // although it is useless, the jump is automatically inserted,
      // since the desugaring process is a purely syntactic operation that
      // does not analyze control-flow
      jump($endswitch)
    }
    $caseDefault:
    {
      revert(0, 0)
      jump($endswitch)
    }
    $endswitch:
  }
  jump($afterFunction)
  allocate:
  {
    // we jump over the unreachable code that introduces the function arguments
    jump($start)
    let $retpos := 0 let size := 0
    $start:
    // output variables live in the same scope as the arguments and is
    // actually allocated.
    let pos := 0
    {
      pos := mload(0x40)
      mstore(0x40, add(pos, size))
    }
    // This code replaces the arguments by the return values and jumps back.
    swap1 pop swap1 jump
    // Again unreachable code that corrects stack height.
    0 0
  }
  f:
  {
    jump($start)
    let $retpos := 0 let x := 0
    $start:
    let y := 0
    {
      let i := 0
      $for_begin:
      jumpi($for_end, iszero(lt(i, x)))
      {
        y := mul(2, y)
      }
      $for_continue:
      { i := add(i, 1) }
      jump($for_begin)
      $for_end:
    } // Here, a pop instruction will be inserted for i
    swap1 pop swap1 jump
    0 0
  }
  $afterFunction:
  stop
}

汇编有下面四个阶段：
1.解析
2.脱汇编（移除switch，for和函数）
3.生成指令流
4.生成字节码
我们将简单的以步骤1到3指定步骤。更加详细的步骤将在后面说明。
解析、语法
解析的任务如下：

• 将字节流转为符号流，去掉其中的C++风格的注释（一种特殊的源代码引用的注释，这里不打算深入讨论）。
• 将符号流转为下述定义的语法结构的AST。
• 注册块中定义的标识符，标注从哪里开始（根据AST节点的注解），变量可以被访问。
  组合词典遵循由Solidity本身定义的词组。
  空格用于分隔标记，它由空格，制表符和换行符组成。 注释是常规的JavaScript / C ++注释，并以与Whitespace相同的方式进行解释。
  语法:

  AssemblyBlock = ‘{‘ AssemblyItem* ‘}‘
  AssemblyItem =
  Identifier |
  AssemblyBlock |
  FunctionalAssemblyExpression |
  AssemblyLocalDefinition |
  FunctionalAssemblyAssignment |
  AssemblyAssignment |
  LabelDefinition |
  AssemblySwitch |
  AssemblyFunctionDefinition |
  AssemblyFor |
  ‘break‘ | ‘continue‘ |
  SubAssembly | ‘dataSize‘ ‘(‘ Identifier ‘)‘ |
  LinkerSymbol |
  ‘errorLabel‘ | ‘bytecodeSize‘ |
  NumberLiteral | StringLiteral | HexLiteral
  Identifier = [a-zA-Z_$] [a-zA-Z_0-9]*
  FunctionalAssemblyExpression = Identifier ‘(‘ ( AssemblyItem ( ‘,‘ AssemblyItem )* )? ‘)‘
  AssemblyLocalDefinition = ‘let‘ IdentifierOrList ‘:=‘ FunctionalAssemblyExpression
  FunctionalAssemblyAssignment = IdentifierOrList ‘:=‘ FunctionalAssemblyExpression
  IdentifierOrList = Identifier | ‘(‘ IdentifierList ‘)‘
  IdentifierList = Identifier ( ‘,‘ Identifier)*
  AssemblyAssignment = ‘=:‘ Identifier
  LabelDefinition = Identifier ‘:‘
  AssemblySwitch = ‘switch‘ FunctionalAssemblyExpression AssemblyCase*
  ( ‘default‘ AssemblyBlock )?
  AssemblyCase = ‘case‘ FunctionalAssemblyExpression AssemblyBlock
  AssemblyFunctionDefinition = ‘function‘ Identifier ‘(‘ IdentifierList? ‘)‘
  ( ‘->‘ ‘(‘ IdentifierList ‘)‘ )? AssemblyBlock
  AssemblyFor = ‘for‘ ( AssemblyBlock | FunctionalAssemblyExpression)
  FunctionalAssemblyExpression ( AssemblyBlock | FunctionalAssemblyExpression) AssemblyBlock
  SubAssembly = ‘assembly‘ Identifier AssemblyBlock
  LinkerSymbol = ‘linkerSymbol‘ ‘(‘ StringLiteral ‘)‘
  NumberLiteral = HexNumber | DecimalNumber
  HexLiteral = ‘hex‘ (‘"‘ ([0-9a-fA-F]{2})* ‘"‘ | ‘\‘‘ ([0-9a-fA-F]{2})* ‘\‘‘)
  StringLiteral = ‘"‘ ([^"\r\n\\] | ‘\\‘ .)* ‘"‘
  HexNumber = ‘0x‘ [0-9a-fA-F]+
  DecimalNumber = [0-9]+

  脱汇编
  一个AST转换，移除其中的for，switch和函数构建。结果仍由同一个解析器，但它不确定使用什么构造。如果添加仅跳转到并且不继续的jumpdests，则添加有关堆栈内容的信息，除非没有局部变量访问到外部作用域或栈高度与上一条指令相同。伪代码如下：

  desugar item: AST -> AST =
  match item {
  AssemblyFunctionDefinition(‘function‘ name ‘(‘ arg1, ..., argn ‘)‘ ‘->‘ ( ‘(‘ ret1, ..., retm ‘)‘ body) ->
  <name>:
  {
  jump($<name>_start)
  let $retPC := 0 let argn := 0 ... let arg1 := 0
  $<name>_start:
  let ret1 := 0 ... let retm := 0
  { desugar(body) }
  swap and pop items so that only ret1, ... retm, $retPC are left on the stack
  jump
  0 (1 + n times) to compensate removal of arg1, ..., argn and $retPC
  }
  AssemblyFor(‘for‘ { init } condition post body) ->
  {
  init // cannot be its own block because we want variable scope to extend into the body
  // find I such that there are no labels $forI_*
  $forI_begin:
  jumpi($forI_end, iszero(condition))
  { body }
  $forI_continue:
  { post }
  jump($forI_begin)
  $forI_end:
  }
  ‘break‘ ->
  {
  // find nearest enclosing scope with label $forI_end
  pop all local variables that are defined at the current point
  but not at $forI_end
  jump($forI_end)
  0 (as many as variables were removed above)
  }
  ‘continue‘ ->
  {
  // find nearest enclosing scope with label $forI_continue
  pop all local variables that are defined at the current point
  but not at $forI_continue
  jump($forI_continue)
  0 (as many as variables were removed above)
  }
  AssemblySwitch(switch condition cases ( default: defaultBlock )? ) ->
  {
  // find I such that there is no $switchI* label or variable
  let $switchI_value := condition
  for each of cases match {
    case val: -> jumpi($switchI_caseJ, eq($switchI_value, val))
  }
  if default block present: ->
    { defaultBlock jump($switchI_end) }
  for each of cases match {
    case val: { body } -> $switchI_caseJ: { body jump($switchI_end) }
  }
  $switchI_end:
  }
  FunctionalAssemblyExpression( identifier(arg1, arg2, ..., argn) ) ->
  {
  if identifier is function <name> with n args and m ret values ->
    {
      // find I such that $funcallI_* does not exist
      $funcallI_return argn  ... arg2 arg1 jump(<name>)
      pop (n + 1 times)
      if the current context is `let (id1, ..., idm) := f(...)` ->
        let id1 := 0 ... let idm := 0
        $funcallI_return:
      else ->
        0 (m times)
        $funcallI_return:
        turn the functional expression that leads to the function call
        into a statement stream
    }
  else -> desugar(children of node)
  }
  default node ->
  desugar(children of node)
  }

  生成操作码流
  在操作码流生成期间，我们在一个计数器中跟踪当前的栈高，所以通过名称访问栈的变量是可能的。栈高在会修改栈的操作码后或每一个标签后进行栈调整。当每一个新局部变量被引入时，它都会用当前的栈高进行注册。如果要访问一个变量（或者拷贝其值，或者对其赋值），会根据当前栈高与变量引入时的当时栈高的不同来选择合适的DUP或SWAP指令。
  伪代码：

  codegen item: AST -> opcode_stream =
  match item {
  AssemblyBlock({ items }) ->
  join(codegen(item) for item in items)
  if last generated opcode has continuing control flow:
  POP for all local variables registered at the block (including variables
  introduced by labels)
  warn if the stack height at this point is not the same as at the start of the block
  Identifier(id) ->
  lookup id in the syntactic stack of blocks
  match type of id
  Local Variable ->
    DUPi where i = 1 + stack_height - stack_height_of_identifier(id)
  Label ->
    // reference to be resolved during bytecode generation
    PUSH<bytecode position of label>
  SubAssembly ->
    PUSH<bytecode position of subassembly data>
  FunctionalAssemblyExpression(id ( arguments ) ) ->
  join(codegen(arg) for arg in arguments.reversed())
  id (which has to be an opcode, might be a function name later)
  AssemblyLocalDefinition(let (id1, ..., idn) := expr) ->
  register identifiers id1, ..., idn as locals in current block at current stack height
  codegen(expr) - assert that expr returns n items to the stack
  FunctionalAssemblyAssignment((id1, ..., idn) := expr) ->
  lookup id1, ..., idn in the syntactic stack of blocks, assert that they are variables
  codegen(expr)
  for j = n, ..., i:
  SWAPi where i = 1 + stack_height - stack_height_of_identifier(idj)
  POP
  AssemblyAssignment(=: id) ->
  look up id in the syntactic stack of blocks, assert that it is a variable
  SWAPi where i = 1 + stack_height - stack_height_of_identifier(id)
  POP
  LabelDefinition(name:) ->
  JUMPDEST
  NumberLiteral(num) ->
  PUSH<num interpreted as decimal and right-aligned>
  HexLiteral(lit) ->
  PUSH32<lit interpreted as hex and left-aligned>
  StringLiteral(lit) ->
  PUSH32<lit utf-8 encoded and left-aligned>
  SubAssembly(assembly <name> block) ->
  append codegen(block) at the end of the code
  dataSize(<name>) ->
  assert that <name> is a subassembly ->
  PUSH32<size of code generated from subassembly <name>>
  linkerSymbol(<lit>) ->
  PUSH32<zeros> and append position to linker table
  }

  参考内容：https://open.juzix.net/doc
  智能合约开发教程视频：区块链系列视频课程之智能合约简介

智能合约从入门到精通：Solidity汇编语言

标签：情况下   变量   制表符   intro   lock   height   blog   根据   嵌套   

原文地址：http://blog.51cto.com/13544628/2137108