core/vm: less allocations for various call variants (#21222)

* core/vm/runtime/tests: add more benchmarks

* core/vm: initial work on improving alloc count for calls to precompiles

name                                  old time/op    new time/op    delta
SimpleLoop/identity-precompile-10M-6     117ms ±75%      43ms ± 1%  -63.09%  (p=0.008 n=5+5)
SimpleLoop/loop-10M-6                   79.6ms ± 4%    70.5ms ± 1%  -11.42%  (p=0.008 n=5+5)

name                                  old alloc/op   new alloc/op   delta
SimpleLoop/identity-precompile-10M-6    24.4MB ± 0%     4.9MB ± 0%  -79.94%  (p=0.008 n=5+5)
SimpleLoop/loop-10M-6                   13.2kB ± 0%    13.2kB ± 0%     ~     (p=0.357 n=5+5)

name                                  old allocs/op  new allocs/op  delta
SimpleLoop/identity-precompile-10M-6      382k ± 0%      153k ± 0%  -59.99%  (p=0.000 n=5+4)
SimpleLoop/loop-10M-6                     40.0 ± 0%      40.0 ± 0%     ~     (all equal)

* core/vm: don't allocate big.int for touch

name                                  old time/op    new time/op    delta
SimpleLoop/identity-precompile-10M-6    43.3ms ± 1%    42.4ms ± 7%     ~     (p=0.151 n=5+5)
SimpleLoop/loop-10M-6                   70.5ms ± 1%    76.7ms ± 1%   +8.67%  (p=0.008 n=5+5)

name                                  old alloc/op   new alloc/op   delta
SimpleLoop/identity-precompile-10M-6    4.90MB ± 0%    2.46MB ± 0%  -49.83%  (p=0.008 n=5+5)
SimpleLoop/loop-10M-6                   13.2kB ± 0%    13.2kB ± 1%     ~     (p=0.571 n=5+5)

name                                  old allocs/op  new allocs/op  delta
SimpleLoop/identity-precompile-10M-6      153k ± 0%       76k ± 0%  -49.98%  (p=0.029 n=4+4)
SimpleLoop/loop-10M-6                     40.0 ± 0%      40.0 ± 0%     ~     (all equal)

* core/vm: reduce allocs in staticcall

name                                  old time/op    new time/op    delta
SimpleLoop/identity-precompile-10M-6    42.4ms ± 7%    37.5ms ± 6%  -11.68%  (p=0.008 n=5+5)
SimpleLoop/loop-10M-6                   76.7ms ± 1%    69.1ms ± 1%   -9.82%  (p=0.008 n=5+5)

name                                  old alloc/op   new alloc/op   delta
SimpleLoop/identity-precompile-10M-6    2.46MB ± 0%    0.02MB ± 0%  -99.35%  (p=0.008 n=5+5)
SimpleLoop/loop-10M-6                   13.2kB ± 1%    13.2kB ± 0%     ~     (p=0.143 n=5+5)

name                                  old allocs/op  new allocs/op  delta
SimpleLoop/identity-precompile-10M-6     76.4k ± 0%      0.1k ± 0%     ~     (p=0.079 n=4+5)
SimpleLoop/loop-10M-6                     40.0 ± 0%      40.0 ± 0%     ~     (all equal)

* trie: better use of hasher keccakState

* core/state/statedb: reduce allocations in getDeletedStateObject

* core/vm: reduce allocations in all call derivates

* core/vm: reduce allocations in call variants

- Make returnstack `uint32`
- Use a `sync.Pool` of `stack`s

* core/vm: fix tests

* core/vm: goimports

* core/vm: tracer fix + staticcall gas fix

* core/vm: add back snapshot to staticcall

* core/vm: review concerns + make returnstack pooled + enable returndata in traces

* core/vm: fix some test tracer method signatures

* core/vm: run gencodec, minor comment polish

Co-authored-by: Péter Szilágyi <peterke@gmail.com>

core/vm/contracts_test.go

@@ -21,7 +21,6 @@ import (
 	"encoding/json"
 	"fmt"
 	"io/ioutil"
-	"math/big"
 	"testing"
 	"time"
 
@@ -72,10 +71,9 @@ var blake2FMalformedInputTests = []precompiledFailureTest{
 func testPrecompiled(addr string, test precompiledTest, t *testing.T) {
 	p := allPrecompiles[common.HexToAddress(addr)]
 	in := common.Hex2Bytes(test.Input)
-	contract := NewContract(AccountRef(common.HexToAddress("1337")),
-		nil, new(big.Int), p.RequiredGas(in))
-	t.Run(fmt.Sprintf("%s-Gas=%d", test.Name, contract.Gas), func(t *testing.T) {
-		if res, err := RunPrecompiledContract(p, in, contract); err != nil {
+	gas := p.RequiredGas(in)
+	t.Run(fmt.Sprintf("%s-Gas=%d", test.Name, gas), func(t *testing.T) {
+		if res, _, err := RunPrecompiledContract(p, in, gas); err != nil {
 			t.Error(err)
 		} else if common.Bytes2Hex(res) != test.Expected {
 			t.Errorf("Expected %v, got %v", test.Expected, common.Bytes2Hex(res))
@@ -91,10 +89,10 @@ func testPrecompiled(addr string, test precompiledTest, t *testing.T) {
 func testPrecompiledOOG(addr string, test precompiledTest, t *testing.T) {
 	p := allPrecompiles[common.HexToAddress(addr)]
 	in := common.Hex2Bytes(test.Input)
-	contract := NewContract(AccountRef(common.HexToAddress("1337")),
-		nil, new(big.Int), p.RequiredGas(in)-1)
-	t.Run(fmt.Sprintf("%s-Gas=%d", test.Name, contract.Gas), func(t *testing.T) {
-		_, err := RunPrecompiledContract(p, in, contract)
+	gas := p.RequiredGas(in) - 1
+
+	t.Run(fmt.Sprintf("%s-Gas=%d", test.Name, gas), func(t *testing.T) {
+		_, _, err := RunPrecompiledContract(p, in, gas)
 		if err.Error() != "out of gas" {
 			t.Errorf("Expected error [out of gas], got [%v]", err)
 		}
@@ -109,11 +107,9 @@ func testPrecompiledOOG(addr string, test precompiledTest, t *testing.T) {
 func testPrecompiledFailure(addr string, test precompiledFailureTest, t *testing.T) {
 	p := allPrecompiles[common.HexToAddress(addr)]
 	in := common.Hex2Bytes(test.Input)
-	contract := NewContract(AccountRef(common.HexToAddress("31337")),
-		nil, new(big.Int), p.RequiredGas(in))
-
+	gas := p.RequiredGas(in)
 	t.Run(test.Name, func(t *testing.T) {
-		_, err := RunPrecompiledContract(p, in, contract)
+		_, _, err := RunPrecompiledContract(p, in, gas)
 		if err.Error() != test.ExpectedError {
 			t.Errorf("Expected error [%v], got [%v]", test.ExpectedError, err)
 		}
@@ -132,8 +128,6 @@ func benchmarkPrecompiled(addr string, test precompiledTest, bench *testing.B) {
 	p := allPrecompiles[common.HexToAddress(addr)]
 	in := common.Hex2Bytes(test.Input)
 	reqGas := p.RequiredGas(in)
-	contract := NewContract(AccountRef(common.HexToAddress("1337")),
-		nil, new(big.Int), reqGas)
 
 	var (
 		res  []byte
@@ -141,14 +135,13 @@ func benchmarkPrecompiled(addr string, test precompiledTest, bench *testing.B) {
 		data = make([]byte, len(in))
 	)
 
-	bench.Run(fmt.Sprintf("%s-Gas=%d", test.Name, contract.Gas), func(bench *testing.B) {
+	bench.Run(fmt.Sprintf("%s-Gas=%d", test.Name, reqGas), func(bench *testing.B) {
 		bench.ReportAllocs()
 		start := time.Now().Nanosecond()
 		bench.ResetTimer()
 		for i := 0; i < bench.N; i++ {
-			contract.Gas = reqGas
 			copy(data, in)
-			res, err = RunPrecompiledContract(p, data, contract)
+			res, _, err = RunPrecompiledContract(p, data, reqGas)
 		}
 		bench.StopTimer()
 		elapsed := float64(time.Now().Nanosecond() - start)