Files
lighthouse/consensus/ssz/src/encode/impls.rs
Paul Hauner fe52322088 Implement SSZ union type (#2579)
## Issue Addressed

NA

## Proposed Changes

Implements the "union" type from the SSZ spec for `ssz`, `ssz_derive`, `tree_hash` and `tree_hash_derive` so it may be derived for `enums`:

https://github.com/ethereum/consensus-specs/blob/v1.1.0-beta.3/ssz/simple-serialize.md#union

The union type is required for the merge, since the `Transaction` type is defined as a single-variant union `Union[OpaqueTransaction]`.

### Crate Updates

This PR will (hopefully) cause CI to publish new versions for the following crates:

- `eth2_ssz_derive`: `0.2.1` -> `0.3.0`
- `eth2_ssz`: `0.3.0` -> `0.4.0`
- `eth2_ssz_types`: `0.2.0` -> `0.2.1`
- `tree_hash`: `0.3.0` -> `0.4.0`
- `tree_hash_derive`: `0.3.0` -> `0.4.0`

These these crates depend on each other, I've had to add a workspace-level `[patch]` for these crates. A follow-up PR will need to remove this patch, ones the new versions are published.

### Union Behaviors

We already had SSZ `Encode` and `TreeHash` derive for enums, however it just did a "transparent" pass-through of the inner value. Since the "union" decoding from the spec is in conflict with the transparent method, I've required that all `enum` have exactly one of the following enum-level attributes:

#### SSZ

-  `#[ssz(enum_behaviour = "union")]`
    - matches the spec used for the merge
-  `#[ssz(enum_behaviour = "transparent")]`
    - maintains existing functionality
    - not supported for `Decode` (never was)
    
#### TreeHash

-  `#[tree_hash(enum_behaviour = "union")]`
    - matches the spec used for the merge
-  `#[tree_hash(enum_behaviour = "transparent")]`
    - maintains existing functionality

This means that we can maintain the existing transparent behaviour, but all existing users will get a compile-time error until they explicitly opt-in to being transparent.

### Legacy Option Encoding

Before this PR, we already had a union-esque encoding for `Option<T>`. However, this was with the *old* SSZ spec where the union selector was 4 bytes. During merge specification, the spec was changed to use 1 byte for the selector.

Whilst the 4-byte `Option` encoding was never used in the spec, we used it in our database. Writing a migrate script for all occurrences of `Option` in the database would be painful, especially since it's used in the `CommitteeCache`. To avoid the migrate script, I added a serde-esque `#[ssz(with = "module")]` field-level attribute to `ssz_derive` so that we can opt into the 4-byte encoding on a field-by-field basis.

The `ssz::legacy::four_byte_impl!` macro allows a one-liner to define the module required for the `#[ssz(with = "module")]` for some `Option<T> where T: Encode + Decode`.

Notably, **I have removed `Encode` and `Decode` impls for `Option`**. I've done this to force a break on downstream users. Like I mentioned, `Option` isn't used in the spec so I don't think it'll be *that* annoying. I think it's nicer than quietly having two different union implementations or quietly breaking the existing `Option` impl.

### Crate Publish Ordering

I've modified the order in which CI publishes crates to ensure that we don't publish a crate without ensuring we already published a crate that it depends upon.

## TODO

- [ ] Queue a follow-up `[patch]`-removing PR.
2021-09-25 05:58:36 +00:00

505 lines
12 KiB
Rust

use super::*;
use core::num::NonZeroUsize;
use ethereum_types::{H256, U128, U256};
use smallvec::SmallVec;
use std::sync::Arc;
macro_rules! impl_encodable_for_uint {
($type: ident, $bit_size: expr) => {
impl Encode for $type {
fn is_ssz_fixed_len() -> bool {
true
}
fn ssz_fixed_len() -> usize {
$bit_size / 8
}
fn ssz_bytes_len(&self) -> usize {
$bit_size / 8
}
fn ssz_append(&self, buf: &mut Vec<u8>) {
buf.extend_from_slice(&self.to_le_bytes());
}
}
};
}
impl_encodable_for_uint!(u8, 8);
impl_encodable_for_uint!(u16, 16);
impl_encodable_for_uint!(u32, 32);
impl_encodable_for_uint!(u64, 64);
#[cfg(target_pointer_width = "32")]
impl_encodable_for_uint!(usize, 32);
#[cfg(target_pointer_width = "64")]
impl_encodable_for_uint!(usize, 64);
// Based on the `tuple_impls` macro from the standard library.
macro_rules! impl_encode_for_tuples {
($(
$Tuple:ident {
$(($idx:tt) -> $T:ident)+
}
)+) => {
$(
impl<$($T: Encode),+> Encode for ($($T,)+) {
fn is_ssz_fixed_len() -> bool {
$(
<$T as Encode>::is_ssz_fixed_len() &&
)*
true
}
fn ssz_fixed_len() -> usize {
if <Self as Encode>::is_ssz_fixed_len() {
$(
<$T as Encode>::ssz_fixed_len() +
)*
0
} else {
BYTES_PER_LENGTH_OFFSET
}
}
fn ssz_bytes_len(&self) -> usize {
if <Self as Encode>::is_ssz_fixed_len() {
<Self as Encode>::ssz_fixed_len()
} else {
let mut len = 0;
$(
len += if <$T as Encode>::is_ssz_fixed_len() {
<$T as Encode>::ssz_fixed_len()
} else {
BYTES_PER_LENGTH_OFFSET +
self.$idx.ssz_bytes_len()
};
)*
len
}
}
fn ssz_append(&self, buf: &mut Vec<u8>) {
let offset = $(
<$T as Encode>::ssz_fixed_len() +
)*
0;
let mut encoder = SszEncoder::container(buf, offset);
$(
encoder.append(&self.$idx);
)*
encoder.finalize();
}
}
)+
}
}
impl_encode_for_tuples! {
Tuple2 {
(0) -> A
(1) -> B
}
Tuple3 {
(0) -> A
(1) -> B
(2) -> C
}
Tuple4 {
(0) -> A
(1) -> B
(2) -> C
(3) -> D
}
Tuple5 {
(0) -> A
(1) -> B
(2) -> C
(3) -> D
(4) -> E
}
Tuple6 {
(0) -> A
(1) -> B
(2) -> C
(3) -> D
(4) -> E
(5) -> F
}
Tuple7 {
(0) -> A
(1) -> B
(2) -> C
(3) -> D
(4) -> E
(5) -> F
(6) -> G
}
Tuple8 {
(0) -> A
(1) -> B
(2) -> C
(3) -> D
(4) -> E
(5) -> F
(6) -> G
(7) -> H
}
Tuple9 {
(0) -> A
(1) -> B
(2) -> C
(3) -> D
(4) -> E
(5) -> F
(6) -> G
(7) -> H
(8) -> I
}
Tuple10 {
(0) -> A
(1) -> B
(2) -> C
(3) -> D
(4) -> E
(5) -> F
(6) -> G
(7) -> H
(8) -> I
(9) -> J
}
Tuple11 {
(0) -> A
(1) -> B
(2) -> C
(3) -> D
(4) -> E
(5) -> F
(6) -> G
(7) -> H
(8) -> I
(9) -> J
(10) -> K
}
Tuple12 {
(0) -> A
(1) -> B
(2) -> C
(3) -> D
(4) -> E
(5) -> F
(6) -> G
(7) -> H
(8) -> I
(9) -> J
(10) -> K
(11) -> L
}
}
impl<T: Encode> Encode for Arc<T> {
fn is_ssz_fixed_len() -> bool {
T::is_ssz_fixed_len()
}
fn ssz_fixed_len() -> usize {
T::ssz_fixed_len()
}
fn ssz_append(&self, buf: &mut Vec<u8>) {
self.as_ref().ssz_append(buf)
}
fn ssz_bytes_len(&self) -> usize {
self.as_ref().ssz_bytes_len()
}
}
macro_rules! impl_for_vec {
($type: ty) => {
impl<T: Encode> Encode for $type {
fn is_ssz_fixed_len() -> bool {
false
}
fn ssz_bytes_len(&self) -> usize {
if <T as Encode>::is_ssz_fixed_len() {
<T as Encode>::ssz_fixed_len() * self.len()
} else {
let mut len = self.iter().map(|item| item.ssz_bytes_len()).sum();
len += BYTES_PER_LENGTH_OFFSET * self.len();
len
}
}
fn ssz_append(&self, buf: &mut Vec<u8>) {
if T::is_ssz_fixed_len() {
buf.reserve(T::ssz_fixed_len() * self.len());
for item in self {
item.ssz_append(buf);
}
} else {
let mut encoder =
SszEncoder::container(buf, self.len() * BYTES_PER_LENGTH_OFFSET);
for item in self {
encoder.append(item);
}
encoder.finalize();
}
}
}
};
}
impl_for_vec!(Vec<T>);
impl_for_vec!(SmallVec<[T; 1]>);
impl_for_vec!(SmallVec<[T; 2]>);
impl_for_vec!(SmallVec<[T; 3]>);
impl_for_vec!(SmallVec<[T; 4]>);
impl_for_vec!(SmallVec<[T; 5]>);
impl_for_vec!(SmallVec<[T; 6]>);
impl_for_vec!(SmallVec<[T; 7]>);
impl_for_vec!(SmallVec<[T; 8]>);
impl Encode for bool {
fn is_ssz_fixed_len() -> bool {
true
}
fn ssz_fixed_len() -> usize {
1
}
fn ssz_bytes_len(&self) -> usize {
1
}
fn ssz_append(&self, buf: &mut Vec<u8>) {
buf.extend_from_slice(&(*self as u8).to_le_bytes());
}
}
impl Encode for NonZeroUsize {
fn is_ssz_fixed_len() -> bool {
<usize as Encode>::is_ssz_fixed_len()
}
fn ssz_fixed_len() -> usize {
<usize as Encode>::ssz_fixed_len()
}
fn ssz_bytes_len(&self) -> usize {
std::mem::size_of::<usize>()
}
fn ssz_append(&self, buf: &mut Vec<u8>) {
self.get().ssz_append(buf)
}
}
impl Encode for H256 {
fn is_ssz_fixed_len() -> bool {
true
}
fn ssz_fixed_len() -> usize {
32
}
fn ssz_bytes_len(&self) -> usize {
32
}
fn ssz_append(&self, buf: &mut Vec<u8>) {
buf.extend_from_slice(self.as_bytes());
}
}
impl Encode for U256 {
fn is_ssz_fixed_len() -> bool {
true
}
fn ssz_fixed_len() -> usize {
32
}
fn ssz_bytes_len(&self) -> usize {
32
}
fn ssz_append(&self, buf: &mut Vec<u8>) {
let n = <Self as Encode>::ssz_fixed_len();
let s = buf.len();
buf.resize(s + n, 0);
self.to_little_endian(&mut buf[s..]);
}
}
impl Encode for U128 {
fn is_ssz_fixed_len() -> bool {
true
}
fn ssz_fixed_len() -> usize {
16
}
fn ssz_bytes_len(&self) -> usize {
16
}
fn ssz_append(&self, buf: &mut Vec<u8>) {
let n = <Self as Encode>::ssz_fixed_len();
let s = buf.len();
buf.resize(s + n, 0);
self.to_little_endian(&mut buf[s..]);
}
}
macro_rules! impl_encodable_for_u8_array {
($len: expr) => {
impl Encode for [u8; $len] {
fn is_ssz_fixed_len() -> bool {
true
}
fn ssz_fixed_len() -> usize {
$len
}
fn ssz_bytes_len(&self) -> usize {
$len
}
fn ssz_append(&self, buf: &mut Vec<u8>) {
buf.extend_from_slice(&self[..]);
}
}
};
}
impl_encodable_for_u8_array!(4);
impl_encodable_for_u8_array!(32);
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn vec_of_u8() {
let vec: Vec<u8> = vec![];
assert_eq!(vec.as_ssz_bytes(), vec![]);
let vec: Vec<u8> = vec![1];
assert_eq!(vec.as_ssz_bytes(), vec![1]);
let vec: Vec<u8> = vec![0, 1, 2, 3];
assert_eq!(vec.as_ssz_bytes(), vec![0, 1, 2, 3]);
}
#[test]
fn vec_of_vec_of_u8() {
let vec: Vec<Vec<u8>> = vec![];
assert_eq!(vec.as_ssz_bytes(), vec![]);
let vec: Vec<Vec<u8>> = vec![vec![]];
assert_eq!(vec.as_ssz_bytes(), vec![4, 0, 0, 0]);
let vec: Vec<Vec<u8>> = vec![vec![], vec![]];
assert_eq!(vec.as_ssz_bytes(), vec![8, 0, 0, 0, 8, 0, 0, 0]);
let vec: Vec<Vec<u8>> = vec![vec![0, 1, 2], vec![11, 22, 33]];
assert_eq!(
vec.as_ssz_bytes(),
vec![8, 0, 0, 0, 11, 0, 0, 0, 0, 1, 2, 11, 22, 33]
);
}
#[test]
fn ssz_encode_u8() {
assert_eq!(0_u8.as_ssz_bytes(), vec![0]);
assert_eq!(1_u8.as_ssz_bytes(), vec![1]);
assert_eq!(100_u8.as_ssz_bytes(), vec![100]);
assert_eq!(255_u8.as_ssz_bytes(), vec![255]);
}
#[test]
fn ssz_encode_u16() {
assert_eq!(1_u16.as_ssz_bytes(), vec![1, 0]);
assert_eq!(100_u16.as_ssz_bytes(), vec![100, 0]);
assert_eq!((1_u16 << 8).as_ssz_bytes(), vec![0, 1]);
assert_eq!(65535_u16.as_ssz_bytes(), vec![255, 255]);
}
#[test]
fn ssz_encode_u32() {
assert_eq!(1_u32.as_ssz_bytes(), vec![1, 0, 0, 0]);
assert_eq!(100_u32.as_ssz_bytes(), vec![100, 0, 0, 0]);
assert_eq!((1_u32 << 16).as_ssz_bytes(), vec![0, 0, 1, 0]);
assert_eq!((1_u32 << 24).as_ssz_bytes(), vec![0, 0, 0, 1]);
assert_eq!((!0_u32).as_ssz_bytes(), vec![255, 255, 255, 255]);
}
#[test]
fn ssz_encode_u64() {
assert_eq!(1_u64.as_ssz_bytes(), vec![1, 0, 0, 0, 0, 0, 0, 0]);
assert_eq!(
(!0_u64).as_ssz_bytes(),
vec![255, 255, 255, 255, 255, 255, 255, 255]
);
}
#[test]
fn ssz_encode_usize() {
assert_eq!(1_usize.as_ssz_bytes(), vec![1, 0, 0, 0, 0, 0, 0, 0]);
assert_eq!(
(!0_usize).as_ssz_bytes(),
vec![255, 255, 255, 255, 255, 255, 255, 255]
);
}
#[test]
fn ssz_encode_bool() {
assert_eq!(true.as_ssz_bytes(), vec![1]);
assert_eq!(false.as_ssz_bytes(), vec![0]);
}
#[test]
fn ssz_encode_h256() {
assert_eq!(H256::from(&[0; 32]).as_ssz_bytes(), vec![0; 32]);
assert_eq!(H256::from(&[1; 32]).as_ssz_bytes(), vec![1; 32]);
let bytes = vec![
1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0,
];
assert_eq!(H256::from_slice(&bytes).as_ssz_bytes(), bytes);
}
#[test]
fn ssz_encode_u8_array_4() {
assert_eq!([0, 0, 0, 0].as_ssz_bytes(), vec![0; 4]);
assert_eq!([1, 0, 0, 0].as_ssz_bytes(), vec![1, 0, 0, 0]);
assert_eq!([1, 2, 3, 4].as_ssz_bytes(), vec![1, 2, 3, 4]);
}
#[test]
fn tuple() {
assert_eq!((10u8, 11u8).as_ssz_bytes(), vec![10, 11]);
assert_eq!((10u32, 11u8).as_ssz_bytes(), vec![10, 0, 0, 0, 11]);
assert_eq!((10u8, 11u8, 12u8).as_ssz_bytes(), vec![10, 11, 12]);
}
}