core/vm: reuse Keccak-256 hashes across opcode executions (#17863)

3 files changed, 48 insertions, 6 deletions

diff --git a/core/vm/instructions.go b/core/vm/instructions.go
index 9623fb8de..e94a2777b 100644
--- a/core/vm/instructions.go
+++ b/core/vm/instructions.go
@@ -24,7 +24,7 @@ import (
 	"github.com/ethereum/go-ethereum/common"
 	"github.com/ethereum/go-ethereum/common/math"
 	"github.com/ethereum/go-ethereum/core/types"
-	"github.com/ethereum/go-ethereum/crypto"
+	"github.com/ethereum/go-ethereum/crypto/sha3"
 	"github.com/ethereum/go-ethereum/params"
 )
 
@@ -373,13 +373,20 @@ func opSAR(pc *uint64, interpreter *EVMInterpreter, contract *Contract, memory *
 func opSha3(pc *uint64, interpreter *EVMInterpreter, contract *Contract, memory *Memory, stack *Stack) ([]byte, error) {
 	offset, size := stack.pop(), stack.pop()
 	data := memory.Get(offset.Int64(), size.Int64())
-	hash := crypto.Keccak256(data)
-	evm := interpreter.evm
 
+	if interpreter.hasher == nil {
+		interpreter.hasher = sha3.NewKeccak256().(keccakState)
+	} else {
+		interpreter.hasher.Reset()
+	}
+	interpreter.hasher.Write(data)
+	interpreter.hasher.Read(interpreter.hasherBuf[:])
+
+	evm := interpreter.evm
 	if evm.vmConfig.EnablePreimageRecording {
-		evm.StateDB.AddPreimage(common.BytesToHash(hash), data)
+		evm.StateDB.AddPreimage(interpreter.hasherBuf, data)
 	}
-	stack.push(interpreter.intPool.get().SetBytes(hash))
+	stack.push(interpreter.intPool.get().SetBytes(interpreter.hasherBuf[:]))
 
 	interpreter.intPool.put(offset, size)
 	return nil, nil
diff --git a/core/vm/instructions_test.go b/core/vm/instructions_test.go
index 73c5befaa..8a48d765d 100644
--- a/core/vm/instructions_test.go
+++ b/core/vm/instructions_test.go
@@ -492,6 +492,27 @@ func BenchmarkOpMstore(bench *testing.B) {
 	poolOfIntPools.put(evmInterpreter.intPool)
 }
 
+func BenchmarkOpSHA3(bench *testing.B) {
+	var (
+		env            = NewEVM(Context{}, nil, params.TestChainConfig, Config{})
+		stack          = newstack()
+		mem            = NewMemory()
+		evmInterpreter = NewEVMInterpreter(env, env.vmConfig)
+	)
+	env.interpreter = evmInterpreter
+	evmInterpreter.intPool = poolOfIntPools.get()
+	mem.Resize(32)
+	pc := uint64(0)
+	start := big.NewInt(0)
+
+	bench.ResetTimer()
+	for i := 0; i < bench.N; i++ {
+		stack.pushN(big.NewInt(32), start)
+		opSha3(&pc, evmInterpreter, nil, mem, stack)
+	}
+	poolOfIntPools.put(evmInterpreter.intPool)
+}
+
 func TestCreate2Addreses(t *testing.T) {
 	type testcase struct {
 		origin   string
diff --git a/core/vm/interpreter.go b/core/vm/interpreter.go
index 8e934f60e..952d96dd4 100644
--- a/core/vm/interpreter.go
+++ b/core/vm/interpreter.go
@@ -18,8 +18,10 @@ package vm
 
 import (
 	"fmt"
+	"hash"
 	"sync/atomic"
 
+	"github.com/ethereum/go-ethereum/common"
 	"github.com/ethereum/go-ethereum/common/math"
 	"github.com/ethereum/go-ethereum/params"
 )
@@ -68,12 +70,24 @@ type Interpreter interface {
 	CanRun([]byte) bool
 }
 
+// keccakState wraps sha3.state. In addition to the usual hash methods, it also supports
+// Read to get a variable amount of data from the hash state. Read is faster than Sum
+// because it doesn't copy the internal state, but also modifies the internal state.
+type keccakState interface {
+	hash.Hash
+	Read([]byte) (int, error)
+}
+
 // EVMInterpreter represents an EVM interpreter
 type EVMInterpreter struct {
 	evm      *EVM
 	cfg      Config
 	gasTable params.GasTable
-	intPool  *intPool
+
+	intPool *intPool
+
+	hasher    keccakState // Keccak256 hasher instance shared across opcodes
+	hasherBuf common.Hash // Keccak256 hasher result array shared aross opcodes
 
 	readOnly   bool   // Whether to throw on stateful modifications
 	returnData []byte // Last CALL's return data for subsequent reuse