• Qian Bin's avatar
    rlp, trie: faster trie node encoding (#24126) · 65ed1a68
    Qian Bin authored
    This change speeds up trie hashing and all other activities that require
    RLP encoding of trie nodes by approximately 20%. The speedup is achieved by
    avoiding reflection overhead during node encoding.
    
    The interface type trie.node now contains a method 'encode' that works with
    rlp.EncoderBuffer. Management of EncoderBuffers is left to calling code.
    trie.hasher, which is pooled to avoid allocations, now maintains an
    EncoderBuffer. This means memory resources related to trie node encoding
    are tied to the hasher pool.
    Co-authored-by: 's avatarFelix Lange <fjl@twurst.com>
    65ed1a68
encode.go 12.1 KB
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471
// Copyright 2014 The go-ethereum Authors
// This file is part of the go-ethereum library.
//
// The go-ethereum library is free software: you can redistribute it and/or modify
// it under the terms of the GNU Lesser General Public License as published by
// the Free Software Foundation, either version 3 of the License, or
// (at your option) any later version.
//
// The go-ethereum library is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
// GNU Lesser General Public License for more details.
//
// You should have received a copy of the GNU Lesser General Public License
// along with the go-ethereum library. If not, see <http://www.gnu.org/licenses/>.

package rlp

import (
	"errors"
	"fmt"
	"io"
	"math/big"
	"reflect"

	"github.com/ethereum/go-ethereum/rlp/internal/rlpstruct"
)

var (
	// Common encoded values.
	// These are useful when implementing EncodeRLP.
	EmptyString = []byte{0x80}
	EmptyList   = []byte{0xC0}
)

var ErrNegativeBigInt = errors.New("rlp: cannot encode negative big.Int")

// Encoder is implemented by types that require custom
// encoding rules or want to encode private fields.
type Encoder interface {
	// EncodeRLP should write the RLP encoding of its receiver to w.
	// If the implementation is a pointer method, it may also be
	// called for nil pointers.
	//
	// Implementations should generate valid RLP. The data written is
	// not verified at the moment, but a future version might. It is
	// recommended to write only a single value but writing multiple
	// values or no value at all is also permitted.
	EncodeRLP(io.Writer) error
}

// Encode writes the RLP encoding of val to w. Note that Encode may
// perform many small writes in some cases. Consider making w
// buffered.
//
// Please see package-level documentation of encoding rules.
func Encode(w io.Writer, val interface{}) error {
	// Optimization: reuse *encBuffer when called by EncodeRLP.
	if buf := encBufferFromWriter(w); buf != nil {
		return buf.encode(val)
	}

	buf := getEncBuffer()
	defer encBufferPool.Put(buf)
	if err := buf.encode(val); err != nil {
		return err
	}
	return buf.writeTo(w)
}

// EncodeToBytes returns the RLP encoding of val.
// Please see package-level documentation for the encoding rules.
func EncodeToBytes(val interface{}) ([]byte, error) {
	buf := getEncBuffer()
	defer encBufferPool.Put(buf)

	if err := buf.encode(val); err != nil {
		return nil, err
	}
	return buf.makeBytes(), nil
}

// EncodeToReader returns a reader from which the RLP encoding of val
// can be read. The returned size is the total size of the encoded
// data.
//
// Please see the documentation of Encode for the encoding rules.
func EncodeToReader(val interface{}) (size int, r io.Reader, err error) {
	buf := getEncBuffer()
	if err := buf.encode(val); err != nil {
		encBufferPool.Put(buf)
		return 0, nil, err
	}
	// Note: can't put the reader back into the pool here
	// because it is held by encReader. The reader puts it
	// back when it has been fully consumed.
	return buf.size(), &encReader{buf: buf}, nil
}

type listhead struct {
	offset int // index of this header in string data
	size   int // total size of encoded data (including list headers)
}

// encode writes head to the given buffer, which must be at least
// 9 bytes long. It returns the encoded bytes.
func (head *listhead) encode(buf []byte) []byte {
	return buf[:puthead(buf, 0xC0, 0xF7, uint64(head.size))]
}

// headsize returns the size of a list or string header
// for a value of the given size.
func headsize(size uint64) int {
	if size < 56 {
		return 1
	}
	return 1 + intsize(size)
}

// puthead writes a list or string header to buf.
// buf must be at least 9 bytes long.
func puthead(buf []byte, smalltag, largetag byte, size uint64) int {
	if size < 56 {
		buf[0] = smalltag + byte(size)
		return 1
	}
	sizesize := putint(buf[1:], size)
	buf[0] = largetag + byte(sizesize)
	return sizesize + 1
}

var encoderInterface = reflect.TypeOf(new(Encoder)).Elem()

// makeWriter creates a writer function for the given type.
func makeWriter(typ reflect.Type, ts rlpstruct.Tags) (writer, error) {
	kind := typ.Kind()
	switch {
	case typ == rawValueType:
		return writeRawValue, nil
	case typ.AssignableTo(reflect.PtrTo(bigInt)):
		return writeBigIntPtr, nil
	case typ.AssignableTo(bigInt):
		return writeBigIntNoPtr, nil
	case kind == reflect.Ptr:
		return makePtrWriter(typ, ts)
	case reflect.PtrTo(typ).Implements(encoderInterface):
		return makeEncoderWriter(typ), nil
	case isUint(kind):
		return writeUint, nil
	case kind == reflect.Bool:
		return writeBool, nil
	case kind == reflect.String:
		return writeString, nil
	case kind == reflect.Slice && isByte(typ.Elem()):
		return writeBytes, nil
	case kind == reflect.Array && isByte(typ.Elem()):
		return makeByteArrayWriter(typ), nil
	case kind == reflect.Slice || kind == reflect.Array:
		return makeSliceWriter(typ, ts)
	case kind == reflect.Struct:
		return makeStructWriter(typ)
	case kind == reflect.Interface:
		return writeInterface, nil
	default:
		return nil, fmt.Errorf("rlp: type %v is not RLP-serializable", typ)
	}
}

func writeRawValue(val reflect.Value, w *encBuffer) error {
	w.str = append(w.str, val.Bytes()...)
	return nil
}

func writeUint(val reflect.Value, w *encBuffer) error {
	w.writeUint64(val.Uint())
	return nil
}

func writeBool(val reflect.Value, w *encBuffer) error {
	w.writeBool(val.Bool())
	return nil
}

func writeBigIntPtr(val reflect.Value, w *encBuffer) error {
	ptr := val.Interface().(*big.Int)
	if ptr == nil {
		w.str = append(w.str, 0x80)
		return nil
	}
	if ptr.Sign() == -1 {
		return ErrNegativeBigInt
	}
	w.writeBigInt(ptr)
	return nil
}

func writeBigIntNoPtr(val reflect.Value, w *encBuffer) error {
	i := val.Interface().(big.Int)
	if i.Sign() == -1 {
		return ErrNegativeBigInt
	}
	w.writeBigInt(&i)
	return nil
}

func writeBytes(val reflect.Value, w *encBuffer) error {
	w.writeBytes(val.Bytes())
	return nil
}

func makeByteArrayWriter(typ reflect.Type) writer {
	switch typ.Len() {
	case 0:
		return writeLengthZeroByteArray
	case 1:
		return writeLengthOneByteArray
	default:
		length := typ.Len()
		return func(val reflect.Value, w *encBuffer) error {
			if !val.CanAddr() {
				// Getting the byte slice of val requires it to be addressable. Make it
				// addressable by copying.
				copy := reflect.New(val.Type()).Elem()
				copy.Set(val)
				val = copy
			}
			slice := byteArrayBytes(val, length)
			w.encodeStringHeader(len(slice))
			w.str = append(w.str, slice...)
			return nil
		}
	}
}

func writeLengthZeroByteArray(val reflect.Value, w *encBuffer) error {
	w.str = append(w.str, 0x80)
	return nil
}

func writeLengthOneByteArray(val reflect.Value, w *encBuffer) error {
	b := byte(val.Index(0).Uint())
	if b <= 0x7f {
		w.str = append(w.str, b)
	} else {
		w.str = append(w.str, 0x81, b)
	}
	return nil
}

func writeString(val reflect.Value, w *encBuffer) error {
	s := val.String()
	if len(s) == 1 && s[0] <= 0x7f {
		// fits single byte, no string header
		w.str = append(w.str, s[0])
	} else {
		w.encodeStringHeader(len(s))
		w.str = append(w.str, s...)
	}
	return nil
}

func writeInterface(val reflect.Value, w *encBuffer) error {
	if val.IsNil() {
		// Write empty list. This is consistent with the previous RLP
		// encoder that we had and should therefore avoid any
		// problems.
		w.str = append(w.str, 0xC0)
		return nil
	}
	eval := val.Elem()
	writer, err := cachedWriter(eval.Type())
	if err != nil {
		return err
	}
	return writer(eval, w)
}

func makeSliceWriter(typ reflect.Type, ts rlpstruct.Tags) (writer, error) {
	etypeinfo := theTC.infoWhileGenerating(typ.Elem(), rlpstruct.Tags{})
	if etypeinfo.writerErr != nil {
		return nil, etypeinfo.writerErr
	}

	var wfn writer
	if ts.Tail {
		// This is for struct tail slices.
		// w.list is not called for them.
		wfn = func(val reflect.Value, w *encBuffer) error {
			vlen := val.Len()
			for i := 0; i < vlen; i++ {
				if err := etypeinfo.writer(val.Index(i), w); err != nil {
					return err
				}
			}
			return nil
		}
	} else {
		// This is for regular slices and arrays.
		wfn = func(val reflect.Value, w *encBuffer) error {
			vlen := val.Len()
			if vlen == 0 {
				w.str = append(w.str, 0xC0)
				return nil
			}
			listOffset := w.list()
			for i := 0; i < vlen; i++ {
				if err := etypeinfo.writer(val.Index(i), w); err != nil {
					return err
				}
			}
			w.listEnd(listOffset)
			return nil
		}
	}
	return wfn, nil
}

func makeStructWriter(typ reflect.Type) (writer, error) {
	fields, err := structFields(typ)
	if err != nil {
		return nil, err
	}
	for _, f := range fields {
		if f.info.writerErr != nil {
			return nil, structFieldError{typ, f.index, f.info.writerErr}
		}
	}

	var writer writer
	firstOptionalField := firstOptionalField(fields)
	if firstOptionalField == len(fields) {
		// This is the writer function for structs without any optional fields.
		writer = func(val reflect.Value, w *encBuffer) error {
			lh := w.list()
			for _, f := range fields {
				if err := f.info.writer(val.Field(f.index), w); err != nil {
					return err
				}
			}
			w.listEnd(lh)
			return nil
		}
	} else {
		// If there are any "optional" fields, the writer needs to perform additional
		// checks to determine the output list length.
		writer = func(val reflect.Value, w *encBuffer) error {
			lastField := len(fields) - 1
			for ; lastField >= firstOptionalField; lastField-- {
				if !val.Field(fields[lastField].index).IsZero() {
					break
				}
			}
			lh := w.list()
			for i := 0; i <= lastField; i++ {
				if err := fields[i].info.writer(val.Field(fields[i].index), w); err != nil {
					return err
				}
			}
			w.listEnd(lh)
			return nil
		}
	}
	return writer, nil
}

func makePtrWriter(typ reflect.Type, ts rlpstruct.Tags) (writer, error) {
	nilEncoding := byte(0xC0)
	if typeNilKind(typ.Elem(), ts) == String {
		nilEncoding = 0x80
	}

	etypeinfo := theTC.infoWhileGenerating(typ.Elem(), rlpstruct.Tags{})
	if etypeinfo.writerErr != nil {
		return nil, etypeinfo.writerErr
	}

	writer := func(val reflect.Value, w *encBuffer) error {
		if ev := val.Elem(); ev.IsValid() {
			return etypeinfo.writer(ev, w)
		}
		w.str = append(w.str, nilEncoding)
		return nil
	}
	return writer, nil
}

func makeEncoderWriter(typ reflect.Type) writer {
	if typ.Implements(encoderInterface) {
		return func(val reflect.Value, w *encBuffer) error {
			return val.Interface().(Encoder).EncodeRLP(w)
		}
	}
	w := func(val reflect.Value, w *encBuffer) error {
		if !val.CanAddr() {
			// package json simply doesn't call MarshalJSON for this case, but encodes the
			// value as if it didn't implement the interface. We don't want to handle it that
			// way.
			return fmt.Errorf("rlp: unadressable value of type %v, EncodeRLP is pointer method", val.Type())
		}
		return val.Addr().Interface().(Encoder).EncodeRLP(w)
	}
	return w
}

// putint writes i to the beginning of b in big endian byte
// order, using the least number of bytes needed to represent i.
func putint(b []byte, i uint64) (size int) {
	switch {
	case i < (1 << 8):
		b[0] = byte(i)
		return 1
	case i < (1 << 16):
		b[0] = byte(i >> 8)
		b[1] = byte(i)
		return 2
	case i < (1 << 24):
		b[0] = byte(i >> 16)
		b[1] = byte(i >> 8)
		b[2] = byte(i)
		return 3
	case i < (1 << 32):
		b[0] = byte(i >> 24)
		b[1] = byte(i >> 16)
		b[2] = byte(i >> 8)
		b[3] = byte(i)
		return 4
	case i < (1 << 40):
		b[0] = byte(i >> 32)
		b[1] = byte(i >> 24)
		b[2] = byte(i >> 16)
		b[3] = byte(i >> 8)
		b[4] = byte(i)
		return 5
	case i < (1 << 48):
		b[0] = byte(i >> 40)
		b[1] = byte(i >> 32)
		b[2] = byte(i >> 24)
		b[3] = byte(i >> 16)
		b[4] = byte(i >> 8)
		b[5] = byte(i)
		return 6
	case i < (1 << 56):
		b[0] = byte(i >> 48)
		b[1] = byte(i >> 40)
		b[2] = byte(i >> 32)
		b[3] = byte(i >> 24)
		b[4] = byte(i >> 16)
		b[5] = byte(i >> 8)
		b[6] = byte(i)
		return 7
	default:
		b[0] = byte(i >> 56)
		b[1] = byte(i >> 48)
		b[2] = byte(i >> 40)
		b[3] = byte(i >> 32)
		b[4] = byte(i >> 24)
		b[5] = byte(i >> 16)
		b[6] = byte(i >> 8)
		b[7] = byte(i)
		return 8
	}
}

// intsize computes the minimum number of bytes required to store i.
func intsize(i uint64) (size int) {
	for size = 1; ; size++ {
		if i >>= 8; i == 0 {
			return size
		}
	}
}