前言

以太坊（ETHereum）是一个开源的有智能合约功能的公共区块链平台，通过其专用加密货币以太坊（ETH）提供去中心化的以太坊虚拟机（EVM）来处理点对点合约。EVM（ETHereum Virtual Machine），以太坊虚拟机的简称，是以太坊的核心之一。智能合约的创建和执行都由EVM来完成，简单来说，EVM是一个状态执行的机器，输入是SOLidity编译后的二进制指令和节点的状态数据，输出是节点状态的改变。

以太坊短地址攻击，最早由Golem团队于2017年4月提出，是由于底层EVM的设计缺陷导致的漏洞。ERC20代币标准定义的转账函数如下：

function transfer(address to, uint256 value) public returns (bool success)

如果传入的to是末端缺省的短地址，EVM会将后面字节补足地址，而**的value值不足则用0填充，导致实际转出的代币数值倍增。

本文从以太坊源码的角度分析EVM底层是如何处理执行智能合约字节码的，并简要分析短地址攻击的原理。

EVM源码分析

evm.go

EVM的源码位于go-ETHereum/core/vm/目录下，在evm.go中定义了EVM结构体，并实现了EVM.Call、EVM.CallCode、EVM.DelegateCall、EVM.StaticCall四种方法来调用智能合约，EVM.Call实现了基本的合约调用的功能，后面三种方法与EVM.Call略有区别，但最终都调用run函数来解析执行智能合约

EVM.Call

// Call executes the contract associated with the addr with the given input as// parameters. It also handles any necessary value transfer required and takes// the necessary steps to create accounts and reverses the state in case of an// execution error or failed value transfer.//hunya// 基本的合约调用func (evm *EVM) Call(caller ContractRef, addr common.Address, input []byte, gas uint64, value *big.Int) (ret []byte, leftOverGas uint64, err error) {    if evm.vmConfig.NoRecursion AMPLAMPL evm.depth gt; 0 {        return nil, gas, nil    }    // Fail if we're trying to execute above the call depth limit    if evm.depth gt; int(params.CallCreateDepth) {        return nil, gas, ErrDepth    }    // Fail if we're trying to transfer more than the available balance    if !evm.Context.CanTransfer(evm.StateDB, caller.Address(), value) {        return nil, gas, ErrInsufficientBalance    }    var (        to       = AccountRef(addr)        snapshot = evm.StateDB.Snapshot()    )    if !evm.StateDB.Exist(addr) {        precompiles := PrecompiledContractsHomestead        if evm.chainRules.Iyzantium {            precompiles = PrecompiledContractyzantium        }        if evm.chainRules.IsIstanbul {            precompiles = PrecompiledContractsIstanbul        }        if precompiles[addr] == nil AMPLAMPL evm.chainRules.IsEIP158 AMPLAMPL value.Sign() == 0 {            // Calling a non existing account, don't do anything, but ping the tracer            if evm.vmConfig.Debug AMPLAMPL evm.depth == 0 {                evm.vmConfig.Tracer.CaptureStart(caller.Address(), addr, false, input, gas, value)                evm.vmConfig.Tracer.CaptureEnd(ret, 0, 0, nil)            }            return nil, gas, nil        }        evm.StateDB.CreateAccount(addr)    }    evm.Transfer(evm.StateDB, caller.Address(), to.Address(), value)    // Initialise a new contract and set the code that is to be used by the EVM.    // The contract is a scoped environment for this execution context on.    contract := NewContract(caller, to, value, gas)    contract.SetCallCode(AMPLaddr, evm.StateDB.GetCodeHash(addr), evm.StateDB.GetCode(addr))    // Even if the account has no code, we need to continue because it might be a precompile    start := time.Now()    // Capture the tracer start/end events in debug mode    // debug模式会捕获tracer的start/end事件    if evm.vmConfig.Debug AMPLAMPL evm.depth == 0 {        evm.vmConfig.Tracer.CaptureStart(caller.Address(), addr, false, input, gas, value)        DeFier func() { // Lazy evaluation of the parameters            evm.vmConfig.Tracer.CaptureEnd(ret, gas-contract.Gas, time.Since(start), err)        }()    }    ret, err = run(evm, contract, input, false)//hunya// 调用run函数执行合约    // When an error was returned by the EVM or when setting the creation code    // above we revert to the snapshot and consume any gas remaining. Additional    // when we're in homestead this also counts for code storage gas errors.    if err != nil {        evm.StateDB.RevertToSnapshot(snapshot)        if err != errExecutionReverted {            contract.UseGas(contract.Gas)        }    }    return ret, contract.Gas, err}

EVM.CallCode

// CallCode executes the contract associated with the addr with the given input// as parameters. It also handles any necessary value transfer required and takes// the necessary steps to create accounts and reverses the state in case of an// execution error or failed value transfer.//// CallCode differs from Call in the sense that it executes the given address'// code with the caller as context.//hunya// 类似SOLidity中的call函数，调用外部合约，执行上下文在被调用合约中func (evm *EVM) CallCode(caller ContractRef, addr common.Address, input []byte, gas uint64, value *big.Int) (ret []byte, leftOverGas uint64, err error) {    if evm.vmConfig.NoRecursion AMPLAMPL evm.depth gt; 0 {        return nil, gas, nil    }    // Fail if we're trying to execute above the call depth limit    if evm.depth gt; int(params.CallCreateDepth) {        return nil, gas, ErrDepth    }    // Fail if we're trying to transfer more than the available balance    if !evm.CanTransfer(evm.StateDB, caller.Address(), value) {        return nil, gas, ErrInsufficientBalance    }    var (        snapshot = evm.StateDB.Snapshot()        to       = AccountRef(caller.Address())    )    // Initialise a new contract and set the code that is to be used by the EVM.    // The contract is a scoped environment for this execution context on.    contract := NewContract(caller, to, value, gas)    contract.SetCallCode(AMPLaddr, evm.StateDB.GetCodeHash(addr), evm.StateDB.GetCode(addr))    ret, err = run(evm, contract, input, false)//hunya// 调用run函数执行合约    if err != nil {        evm.StateDB.RevertToSnapshot(snapshot)        if err != errExecutionReverted {            contract.UseGas(contract.Gas)        }    }    return ret, contract.Gas, err}

EVM.DelegateCall

// DelegateCall executes the contract associated with the addr with the given input// as parameters. It reverses the state in case of an execution error.//// DelegateCall differs from CallCode in the sense that it executes the given address'// code with the caller as context and the caller is set to the caller of the caller.//hunya// 类似SOLidity中的delegatecall函数，调用外部合约，执行上下文在调用合约中func (evm *EVM) DelegateCall(caller ContractRef, addr common.Address, input []byte, gas uint64) (ret []byte, leftOverGas uint64, err error) {    if evm.vmConfig.NoRecursion AMPLAMPL evm.depth gt; 0 {        return nil, gas, nil    }    // Fail if we're trying to execute above the call depth limit    if evm.depth gt; int(params.CallCreateDepth) {        return nil, gas, ErrDepth    }    var (        snapshot = evm.StateDB.Snapshot()        to       = AccountRef(caller.Address())    )    // Initialise a new contract and make initialise the delegate values    contract := NewContract(caller, to, nil, gas).AsDelegate()    contract.SetCallCode(AMPLaddr, evm.StateDB.GetCodeHash(addr), evm.StateDB.GetCode(addr))    ret, err = run(evm, contract, input, false)//hunya// 调用run函数执行合约    if err != nil {        evm.StateDB.RevertToSnapshot(snapshot)        if err != errExecutionReverted {            contract.UseGas(contract.Gas)        }    }    return ret, contract.Gas, err}

EVM.StaticCall

// StaticCall executes the contract associated with the addr with the given input// as parameters while disallowing any modifications to the state during the call.// Opcodes that attempt to perform such modifications will result in exceptions// instead of performing the modifications.//hunya// 与EVM.Call类似，但不允许执行会修改**存储的数据的指令func (evm *EVM) StaticCall(caller ContractRef, addr common.Address, input []byte, gas uint64) (ret []byte, leftOverGas uint64, err error) {    if evm.vmConfig.NoRecursion AMPLAMPL evm.depth gt; 0 {        return nil, gas, nil    }    // Fail if we're trying to execute above the call depth limit    if evm.depth gt; int(params.CallCreateDepth) {        return nil, gas, ErrDepth    }    var (        to       = AccountRef(addr)        snapshot = evm.StateDB.Snapshot()    )    // Initialise a new contract and set the code that is to be used by the EVM.    // The contract is a scoped environment for this execution context on.    contract := NewContract(caller, to, new(big.Int), gas)    contract.SetCallCode(AMPLaddr, evm.StateDB.GetCodeHash(addr), evm.StateDB.GetCode(addr))    // We do an AddBalance of zero here, just in order to trigger a touch.    // This doesn't matter on Mainnet, where all empties are gone at the time of Byzantium,    // but is the correct thing to do and matters on other networks, in tests, and potential    // future scenarios    evm.StateDB.AddBalance(addr, bigZero)    // When an error was returned by the EVM or when setting the creation code    // above we revert to the snapshot and consume any gas remaining. Additional    // when we're in Homestead this also counts for code storage gas errors.    ret, err = run(evm, contract, input, true)//hunya// 调用run函数执行合约    if err != nil {        evm.StateDB.RevertToSnapshot(snapshot)        if err != errExecutionReverted {            contract.UseGas(contract.Gas)        }    }    return ret, contract.Gas, err}

run函数前半段是判断是否是以太坊内置预编译的特殊合约，有单独的运行方式

后半段则是对于一般的合约调用解释器interpreter去执行调用

interpreter.go

解释器相关代码在interpreter.go中，interpreter是一个接口，目前仅有EVMInterpreter这一个具体实现

合约经由EVM.Call调用Interpreter.Run来到EVMInpreter.Run

EVMInterpreter的Run方法代码较长，其中处理执行合约字节码的主循环如下：

大部分代码主要是检查准备运行环境，执行合约字节码的核心代码主要是以下3行

op = contract.GetOp(pc)operation := in.cfg.JumpTable[op]......res, err = operation.execute(AMPLpc, in, contract, mem, stack)......

interpreter的主要工作实际上只是通过JumpTable查找指令，起到一个翻译解析的作用

最终的执行是通过调用operation对象的execute方法

jump_table.go

operation的定义位于jump_table.go中

jump_table.go中还定义了JumpTable和多种不同的指令集

在基本指令中心化有三个处理input的指令，分别是CALLDATALOAD、CALLDATASIZE和CALLDATACOPY

jump_table.go中的代码同样只是起到解析的功能，提供了指令的查找，定义了每个指令具体的执行函数

instructions.go

instructions.go中是所有指令的具体实现，上述三个函数的具体实现如下：

这三个函数的作用分别是从input加载参数入栈、获取input大小、**input中的参数到内存

我们重点关注opCallDataLoad函数是如何处理input中的参数入栈的

opCallDataLoad函数调用getDataBig函数，传入contract.Input、stack.pop()和big32，将结果转为big.Int入栈

getDataBig函数以stack.pop()栈顶元素作为起始索引，截取input中big32大小的数据，然后传入common.RightPadBytes处理并返回

其中涉及到的另外两个函数math.BigMin和common.RightPadBytes如下：

//file: go-thereum/common/math/big.gofunc BigMin(x, y *big.Int) *big.Int {    if x.Cmp(y) gt; 0 {        return y    }    return x}//file: go-ETHereum/common/bytes.gofunc RightPadBytes(slice []byte, l int) []byte {    if l lt;= len(slice) {        return slice    }    //右填充0x00至l位    padded := make([]byte, l)    copy(padded, slice)    return padded}

分析到这里，基本上已经能很明显看到问题所在了

RightPadBytes函数会将传入的字节切片右填充至l位长度，而l是被传入的big32，即32位长度

所以在短地址攻击中，调用的transfer(address to, uint256 value)函数，如果to是低位缺省的地址，由于EVM在处理时是固定截取32位长度的，所以会将value数值高位补的0算进to的末端，而在截取value时由于位数不够32位，则又填充0x00至32位，最终导致转账的value指数级增大。

测试与复现

编写一个简单的合约来测试

pragma SOLidity ^0.5.0;contract Test {    uint256 internal _totalSupp;    mapping(address =gt; uint256) internal _balances;    event Transfer(address indexed from, address indexed to, uint256 value);    constructor() public {        _totalSupp = 1 * 10 ** 18;        _balances[msg.sender] = _totalSupp;    }    function totalSupp() external view returns (uint256) {        return _totalSupp;    }    function balanceOf(address account) external view returns (uint256) {        return _balances[account];    }    function transfer(address to,uint256 value) public returns (bool) {        require(to != address(0));        require(_balances[msg.sender] gt;= value);        require(_balances[to] + value gt;= _balances[to]);        _balances[msg.sender] -= value;        _balances[to] += value;        emit Transfer(msg.sender, to, value);    }}

remix部署，调用transfer发起正常的转账

input为0xa9059cbb00000000000000000000000071430fd8c82cc7b991a8455fc6ea5b37a06d393f0000000000000000000000000000000000000000000000000000000000000001

直接尝试短地址攻击，删去转账地址的后两位，会发现并不能通过，remix会直接报错

这是因为web3.做了校验，web3.是用户与以太坊节点交互的媒介

源码复现

通过源码函数复现如下：

实际复现

至于如何完成实际场景的攻击，可以参考文末的链接[1]，利用web3.ETH.sendSignedTransaction绕过限制

实际上，web3.做的校验仅限于显式传入转账地址的函数，如web3.ETH.sendTransaction这种，像web3.ETH.sendSignedTransaction、web3.ETH.sendRawTransaction这种传入的参数是序列化后的数据的就校验不了，是可以完成短地址攻击的，感兴趣的可以自己尝试，这里就不多写了

PS：文中分析的go-ETHereum源码版本是commit-fdff182，源码与**版有些出入，但**版的也未修复这种缺陷（可能官方不认为这是缺陷?），分析思路依然可以沿用

思考

以太坊底层EVM并没有修复短地址攻击的这么一个缺陷，而是直接在web3.里对地址做的校验，目前各种合约或多或少也做了校验，所以虽然EVM底层可以复现，但实际场景中问题应该不大，但如果是开放RPC的节点可能还是会存在这种风险

另外还有一个点，按底层EVM的这种机制，易受攻击的应该不仅仅是transfer(address to, uint256 value)这个点，只是因为这个函数是ERC20代币标准，而且参数的设计恰好能导致涉及金额的短地址攻击，并且特殊的地址易构造，所以这个函数常作为短地址攻击的典。在其他的一些非代币合约，如竞猜、游戏类的合约中，一些非转账类的事务处理函数中，如果不对类似地址这种的参数做长度校验，可能也存在类似短地址攻击的风险，也或者并不局限于地址，可能还有其他的利用方式还没挖矿出来。

参考

[1] 以太坊短地址攻击详解

https://www.anquanke.com/post/id/159453/https://www.anquanke.com/post/id/159453

[2] 以太坊源码解析：evm

https://www.jianshu.com/p/f319c78e9714/https://www.jianshu.com/p/f319c78e9714

本文由知道创宇404实验室原创发布
转载，请参考转载声明，注明出处： https://www.anquanke.com/post/id/214757