上一节分析了同步一个新的区块准备插入本地BlockChain之前需要重放并执行新区块的所有交易,并产生交易收据和日志。以太坊是如何执行这些交易呢?这就要请出大名鼎鼎的以太坊虚拟机。 以太坊虚拟机在执行交易分为两个部分,第一部分是创建EVM,计算交易金额,设置交易对象,计算交易gas花销;第二部分是EVM 的虚拟机解析器通过合约指令,执行智能合约代码,具体来看看源码。
一,创建EVM,通过EVM执行交易流程 上一节分析BlockChain调用processor.Process()遍历block的所有交易,然后调用:
receipt, _, err := ApplyTransaction(p.config, p.bc, nil, gp, statedb, header, tx, usedGas, cfg)。执行交易并返回收据数据
func ApplyTransaction(config *params.ChainConfig, bc *BlockChain, author *common.Address, gp *GasPool, statedb *state.StateDB, header *types.Header, tx *types.Transaction, usedGas *uint64, cfg vm.Config) (*types.Receipt, uint64, error) { msg, err := tx.AsMessage(types.MakeSigner(config, header.Number)) if err != nil { return nil, 0, err } // Create a new context to be used in the EVM environment context := NewEVMContext(msg, header, bc, author) // Create a new environment which holds all relevant information // about the transaction and calling mechanisms. vmenv := vm.NewEVM(context, statedb, config, cfg) // Apply the transaction to the current state (included in the env) _, gas, failed, err := ApplyMessage(vmenv, msg, gp) if err != nil { return nil, 0, err } // Update the state with pending changes var root []byte if config.IsByzantium(header.Number) { statedb.Finalise(true) } else { root = statedb.IntermediateRoot(config.IsEIP158(header.Number)).Bytes() } *usedGas += gas // Create a new receipt for the transaction, storing the intermediate root and gas used by the tx // based on the eip phase, we're passing wether the root touch-delete accounts. receipt := types.NewReceipt(root, failed, *usedGas) receipt.TxHash = tx.Hash() receipt.GasUsed = gas // if the transaction created a contract, store the creation address in the receipt. if msg.To() == nil { receipt.ContractAddress = crypto.CreateAddress(vmenv.Context.Origin, tx.Nonce()) } // Set the receipt logs and create a bloom for filtering receipt.Logs = statedb.GetLogs(tx.Hash()) receipt.Bloom = types.CreateBloom(types.Receipts{receipt}) return receipt, gas, err }1,首先调用tx.Message()方法产生交易Message。这个方法通过txdata数据来拼接Message对象,并通过签名方法signer.Sender(tx),对txdata 的V、R 、S三个数进行解密得到这个交易的签名公钥(也是就是发送方的地址)。发送方的地址在交易数据中是没有的,这主要是为了防止交易数据被篡改,任何交易数据的变化后通过signer.Sender方法都不能得到正确的地址。 2,调用 NewEVMContext(msg, header, bc, author)创建EVM的上下文环境,调用vm.NewEVM(context, statedb, config, cfg)创建EVM对象,并在内部创建一个evm.interpreter(虚拟机解析器)。 3,调用ApplyMessage(vmenv, msg, gp)方法通过EVM对象来执行Message。 重点看看ApplyMessage()方法的实现:
func ApplyMessage(evm *vm.EVM, msg Message, gp *GasPool) ([]byte, uint64, bool, error) { return NewStateTransition(evm, msg, gp).TransitionDb() }创建stateTransition对象,执行TransitionDb()方法:
func (st *StateTransition) TransitionDb() (ret []byte, usedGas uint64, failed bool, err error) { if err = st.preCheck(); err != nil { return } msg := st.msg sender := st.from() // err checked in preCheck homestead := st.evm.ChainConfig().IsHomestead(st.evm.BlockNumber) contractCreation := msg.To() == nil // Pay intrinsic gas gas, err := IntrinsicGas(st.data, contractCreation, homestead) if err != nil { return nil, 0, false, err } if err = st.useGas(gas); err != nil { return nil, 0, false, err } var ( evm = st.evm // vm errors do not effect consensus and are therefor // not assigned to err, except for insufficient balance // error. vmerr error ) if contractCreation { ret, _, st.gas, vmerr = evm.Create(sender, st.data, st.gas, st.value) } else { // Increment the nonce for the next transaction st.state.SetNonce(sender.Address(), st.state.GetNonce(sender.Address())+1) ret, st.gas, vmerr = evm.Call(sender, st.to().Address(), st.data, st.gas, st.value) } if vmerr != nil { log.Debug("VM returned with error", "err", vmerr) // The only possible consensus-error would be if there wasn't // sufficient balance to make the transfer happen. The first // balance transfer may never fail. if vmerr == vm.ErrInsufficientBalance { return nil, 0, false, vmerr } } st.refundGas() st.state.AddBalance(st.evm.Coinbase, new(big.Int).Mul(new(big.Int).SetUint64(st.gasUsed()), st.gasPrice)) return ret, st.gasUsed(), vmerr != nil, err }3.1,调用IntrinsicGas()方法,通过计算消息的大小以及是否是合约创建交易,来计算此次交易需消耗的gas。 3.2,如果是合约创建交易,调用evm.Create(sender, st.data, st.gas, st.value)来执行message
func (evm *EVM) Create(caller ContractRef, code []byte, gas uint64, value *big.Int) (ret []byte, contractAddr common.Address, leftOverGas uint64, err error) { // Depth check execution. Fail if we're trying to execute above the // limit. if evm.depth > int(params.CallCreateDepth) { return nil, common.Address{}, gas, ErrDepth } if !evm.CanTransfer(evm.StateDB, caller.Address(), value) { return nil, common.Address{}, gas, ErrInsufficientBalance } // Ensure there's no existing contract already at the designated address nonce := evm.StateDB.GetNonce(caller.Address()) evm.StateDB.SetNonce(caller.Address(), nonce+1) contractAddr = crypto.CreateAddress(caller.Address(), nonce) contractHash := evm.StateDB.GetCodeHash(contractAddr) if evm.StateDB.GetNonce(contractAddr) != 0 || (contractHash != (common.Hash{}) && contractHash != emptyCodeHash) { return nil, common.Address{}, 0, ErrContractAddressCollision } // Create a new account on the state snapshot := evm.StateDB.Snapshot() evm.StateDB.CreateAccount(contractAddr) if evm.ChainConfig().IsEIP158(evm.BlockNumber) { evm.StateDB.SetNonce(contractAddr, 1) } evm.Transfer(evm.StateDB, caller.Address(), contractAddr, value) // initialise a new contract and set the code that is to be used by the // E The contract is a scoped evmironment for this execution context // only. contract := NewContract(caller, AccountRef(contractAddr), value, gas) contract.SetCallCode(&contractAddr, crypto.Keccak256Hash(code), code) if evm.vmConfig.NoRecursion && evm.depth > 0 { return nil, contractAddr, gas, nil } if evm.vmConfig.Debug && evm.depth == 0 { evm.vmConfig.Tracer.CaptureStart(caller.Address(), contractAddr, true, code, gas, value) } start := time.Now() ret, err = run(evm, contract, nil) // check whether the max code size has been exceeded maxCodeSizeExceeded := evm.ChainConfig().IsEIP158(evm.BlockNumber) && len(ret) > params.MaxCodeSize // if the contract creation ran successfully and no errors were returned // calculate the gas required to store the code. If the code could not // be stored due to not enough gas set an error and let it be handled // by the error checking condition below. if err == nil && !maxCodeSizeExceeded { createDataGas := uint64(len(ret)) * params.CreateDataGas if contract.UseGas(createDataGas) { evm.StateDB.SetCode(contractAddr, ret) } else { err = ErrCodeStoreOutOfGas } } // 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. Additionally // when we're in homestead this also counts for code storage gas errors. if maxCodeSizeExceeded || (err != nil && (evm.ChainConfig().IsHomestead(evm.BlockNumber) || err != ErrCodeStoreOutOfGas)) { evm.StateDB.RevertToSnapshot(snapshot) if err != errExecutionReverted { contract.UseGas(contract.Gas) } } // Assign err if contract code size exceeds the max while the err is still empty. if maxCodeSizeExceeded && err == nil { err = errMaxCodeSizeExceeded } if evm.vmConfig.Debug && evm.depth == 0 { evm.vmConfig.Tracer.CaptureEnd(ret, gas-contract.Gas, time.Since(start), err) } return ret, contractAddr, contract.Gas, err }3.2.1,evm执行栈深度不能超过1024,发送方持有的以太坊数量大于此次合约交易金额。 3.2.2,对该发送方地址的nonce值+1,通过地址和nonce值生成合约地址,通过合约地址得到合约hash值。 3.2.3,记录一个状态快照,用来后见失败回滚。 3.2.4,为这个合约地址创建一个合约账户,并为这个合约账户设置nonce值为1 3.2.5,产生以太坊资产转移,发送方地址账户金额减value值,合约账户的金额加value值。 3.2.6,根据发送方地址和合约地址,以及金额value 值和gas,合约代码和代码hash值,创建一个合约对象 3.2.7,run方法来执行合约,内部调用evm的解析器来执行合约指令,如果是预编译好的合约,则预编译执行合约就行。 3.2.8,如果执行ok,setcode更新这个合约地址状态,设置usegas为创建合约的gas。如果执行出错,则回滚到之前快照状态,设置usegas为传入的合约gas。
3.3,如果不是新创建的合约,则调用evm.Call(sender, st.to().Address(), st.data, st.gas, st.value)方法,同时更新发送方地址nonce值+1.
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 && evm.depth > 0 { return nil, gas, nil } // Fail if we're trying to execute above the call depth limit if evm.depth > 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.ChainConfig().IsByzantium(evm.BlockNumber) { precompiles = PrecompiledContractsByzantium } if precompiles[addr] == nil && evm.ChainConfig().IsEIP158(evm.BlockNumber) && value.Sign() == 0 { 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 only. contract := NewContract(caller, to, value, gas) contract.SetCallCode(&addr, evm.StateDB.GetCodeHash(addr), evm.StateDB.GetCode(addr)) start := time.Now() // Capture the tracer start/end events in debug mode if evm.vmConfig.Debug && evm.depth == 0 { evm.vmConfig.Tracer.CaptureStart(caller.Address(), addr, false, input, gas, value) defer func() { // Lazy evaluation of the parameters evm.vmConfig.Tracer.CaptureEnd(ret, gas-contract.Gas, time.Since(start), err) }() } ret, err = run(evm, contract, input) // 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. Additionally // 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.call方法和evm.create方法大致相同,我们来说说不一样的地方。 3.3.1,call方法调用的是一个存在的合约地址的合约,所以不用创建合约账户。如果call方法发现本地没有合约接收方的账户,则需要创建一个接收方的账户,并更新本地状态数据库。 3.3.2,create方法的资金transfer转移是在创建合约用户账户和这个合约账户之间发生,而call方法的资金转移是在合约的发送方和合约的接收方之间产生。
3.4,TransitionDb()方法执行完合约,调用st.refundGas()方法计算合约退税,调用evm SSTORE指令 或者evm SUICIDE指令销毁合约十都会产生退税。 3.5,计算合约产生的gas总数,加入到矿工账户,作为矿工收入。
4,回到最开始的ApplyTransaction()方法,根据EVM的执行结果,拼接交易receipt数据,其中receipt.Logs日志数据是EVM执行指令代码的时候产生的,receipt.Bloom根据日志数据建立bloom过滤器。
二,EVM 的虚拟机解析器通过运行合约指令,执行智能合约代码 我们从 3.2.7 执行合约的run()方法入手,它调用了evm.interpreter.Run(contract, input)方法
func (in *Interpreter) Run(contract *Contract, input []byte) (ret []byte, err error) { // Increment the call depth which is restricted to 1024 in.evm.depth++ defer func() { in.evm.depth-- }() // Reset the previous call's return data. It's unimportant to preserve the old buffer // as every returning call will return new data anyway. in.returnData = nil // Don't bother with the execution if there's no code. if len(contract.Code) == 0 { return nil, nil } var ( op OpCode // current opcode mem = NewMemory() // bound memory stack = newstack() // local stack // For optimisation reason we're using uint64 as the program counter. // It's theoretically possible to go above 2^64. The YP defines the PC // to be uint256. Practically much less so feasible. pc = uint64(0) // program counter cost uint64 // copies used by tracer pcCopy uint64 // needed for the deferred Tracer gasCopy uint64 // for Tracer to log gas remaining before execution logged bool // deferred Tracer should ignore already logged steps ) contract.Input = input if in.cfg.Debug { defer func() { if err != nil { if !logged { in.cfg.Tracer.CaptureState(in.evm, pcCopy, op, gasCopy, cost, mem, stack, contract, in.evm.depth, err) } else { in.cfg.Tracer.CaptureFault(in.evm, pcCopy, op, gasCopy, cost, mem, stack, contract, in.evm.depth, err) } } }() } // The Interpreter main run loop (contextual). This loop runs until either an // explicit STOP, RETURN or SELFDESTRUCT is executed, an error occurred during // the execution of one of the operations or until the done flag is set by the // parent context. for atomic.LoadInt32(&in.evm.abort) == 0 { if in.cfg.Debug { // Capture pre-execution values for tracing. logged, pcCopy, gasCopy = false, pc, contract.Gas } // Get the operation from the jump table and validate the stack to ensure there are // enough stack items available to perform the operation. op = contract.GetOp(pc) operation := in.cfg.JumpTable[op] if !operation.valid { return nil, fmt.Errorf("invalid opcode 0x%x", int(op)) } if err := operation.validateStack(stack); err != nil { return nil, err } // If the operation is valid, enforce and write restrictions if err := in.enforceRestrictions(op, operation, stack); err != nil { return nil, err } var memorySize uint64 // calculate the new memory size and expand the memory to fit // the operation if operation.memorySize != nil { memSize, overflow := bigUint64(operation.memorySize(stack)) if overflow { return nil, errGasUintOverflow } // memory is expanded in words of 32 bytes. Gas // is also calculated in words. if memorySize, overflow = math.SafeMul(toWordSize(memSize), 32); overflow { return nil, errGasUintOverflow } } if !in.cfg.DisableGasMetering { // consume the gas and return an error if not enough gas is available. // cost is explicitly set so that the capture state defer method cas get the proper cost cost, err = operation.gasCost(in.gasTable, in.evm, contract, stack, mem, memorySize) if err != nil || !contract.UseGas(cost) { return nil, ErrOutOfGas } } if memorySize > 0 { mem.Resize(memorySize) } if in.cfg.Debug { in.cfg.Tracer.CaptureState(in.evm, pc, op, gasCopy, cost, mem, stack, contract, in.evm.depth, err) logged = true } // execute the operation res, err := operation.execute(&pc, in.evm, contract, mem, stack) // verifyPool is a build flag. Pool verification makes sure the integrity // of the integer pool by comparing values to a default value. if verifyPool { verifyIntegerPool(in.intPool) } // if the operation clears the return data (e.g. it has returning data) // set the last return to the result of the operation. if operation.returns { in.returnData = res } switch { case err != nil: return nil, err case operation.reverts: return res, errExecutionReverted case operation.halts: return res, nil case !operation.jumps: pc++ } } return nil, nil }我们直接看解析器处理的主循环,之前的代码都是在初始化一些临时变量。 1,首先调用contract.GetOp(pc)从和约二进制数据里取得第pc个opcode,opcode是以太坊虚拟机指令,一共不超过256个,正好一个byte大小能装下。 2,从解析器的JumpTable表中查到op对应的operation。比如opcode是SHA3(0x20),取到的operation就是
SHA3: { execute: opSha3, gasCost: gasSha3, validateStack: makeStackFunc(2, 1), memorySize: memorySha3, valid: true, }execute表示指令对应的执行方法 gasCost表示执行这个指令需要消耗的gas validateStack计算是不是解析器栈溢出 memorySize用于计算operation的占用内存大小
3,如果operation可用,解析器栈不超过1024,且读写不冲突 4,计算operation的memorysize,不能大于64位。 5,根据不同的指令,指令的memorysize等,调用operation.gasCost()方法计算执行operation指令需要消耗的gas。 6,调用operation.execute(&pc, in.evm, contract, mem, stack)执行指令对应的方法。 7,operation.reverts值是true或者operation.halts值是true的指令,会跳出主循环,否则继续遍历下个op。 8,operation指令集里面有4个特殊的指令LOG0,LOG1,LOG2,LOG3,它们的指令执行方法makeLog()会产生日志数据,日志内容包括EVM解析栈内容,指令内存数据,区块信息,合约信息等。这些日志数据会写入到tx的Receipt的logs里面,并存入本地ldb数据库。
总结 EVM是以太坊的核心功能,得益于EVM,以太坊把区块链带入了2.0时代,这是一个非常伟大的进步。