Files
serai/coordinator/src/tests/tributary/dkg.rs

372 lines
12 KiB
Rust
Raw Normal View History

use core::time::Duration;
2023-04-23 02:18:41 -04:00
use std::collections::HashMap;
use zeroize::Zeroizing;
use rand_core::{RngCore, OsRng};
use scale::Decode;
use ciphersuite::{group::GroupEncoding, Ciphersuite, Ristretto};
use frost::Participant;
use sp_runtime::traits::Verify;
use tokio::time::sleep;
use serai_db::{DbTxn, Db, MemDb};
use processor_messages::{
key_gen::{self, KeyGenId},
CoordinatorMessage,
};
Slash malevolent validators (#294) * add slash tx * ignore unsigned tx replays * verify that provided evidence is valid * fix clippy + fmt * move application tx handling to another module * partially handle the tendermint txs * fix pr comments * support unsigned app txs * add slash target to the votes * enforce provided, unsigned, signed tx ordering within a block * bug fixes * add unit test for tendermint txs * bug fixes * update tests for tendermint txs * add tx ordering test * tidy up tx ordering test * cargo +nightly fmt * Misc fixes from rebasing * Finish resolving clippy * Remove sha3 from tendermint-machine * Resolve a DoS in SlashEvidence's read Also moves Evidence from Vec<Message> to (Message, Option<Message>). That should meet all requirements while being a bit safer. * Make lazy_static a dev-depend for tributary * Various small tweaks One use of sort was inefficient, sorting unsigned || signed when unsigned was already properly sorted. Given how the unsigned TXs were given a nonce of 0, an unstable sort may swap places with an unsigned TX and a signed TX with a nonce of 0 (leading to a faulty block). The extra protection added here sorts signed, then concats. * Fix Tributary tests I broke, start review on tendermint/tx.rs * Finish reviewing everything outside tests and empty_signature * Remove empty_signature empty_signature led to corrupted local state histories. Unfortunately, the API is only sane with a signature. We now use the actual signature, which risks creating a signature over a malicious message if we have ever have an invariant producing malicious messages. Prior, we only signed the message after the local machine confirmed it was okay per the local view of consensus. This is tolerated/preferred over a corrupt state history since production of such messages is already an invariant. TODOs are added to make handling of this theoretical invariant further robust. * Remove async_sequential for tokio::test There was no competition for resources forcing them to be run sequentially. * Modify block order test to be statistically significant without multiple runs * Clean tests --------- Co-authored-by: Luke Parker <lukeparker5132@gmail.com>
2023-08-21 07:28:23 +03:00
use tributary::{TransactionTrait, Tributary};
use crate::{
tributary::{TributaryDb, Transaction, TributarySpec, scanner::handle_new_blocks},
tests::{
MemProcessors, LocalP2p,
tributary::{new_keys, new_spec, new_tributaries, run_tributaries, wait_for_tx_inclusion},
},
};
#[tokio::test]
2023-04-23 02:18:41 -04:00
async fn dkg_test() {
let keys = new_keys(&mut OsRng);
let spec = new_spec(&mut OsRng, &keys);
let tributaries = new_tributaries(&keys, &spec).await;
// Run the tributaries in the background
tokio::spawn(run_tributaries(tributaries.clone()));
let mut txs = vec![];
// Create DKG commitments for each key
for key in &keys {
let attempt = 0;
let mut commitments = vec![0; 256];
OsRng.fill_bytes(&mut commitments);
2023-04-23 02:18:41 -04:00
let mut tx = Transaction::DkgCommitments(attempt, commitments, Transaction::empty_signed());
tx.sign(&mut OsRng, spec.genesis(), key, 0);
txs.push(tx);
}
let block_before_tx = tributaries[0].1.tip().await;
// Publish all commitments but one
for (i, tx) in txs.iter().enumerate().skip(1) {
assert!(tributaries[i].1.add_transaction(tx.clone()).await);
}
// Wait until these are included
for tx in txs.iter().skip(1) {
wait_for_tx_inclusion(&tributaries[0].1, block_before_tx, tx.hash()).await;
}
let expected_commitments: HashMap<_, _> = txs
.iter()
.enumerate()
.map(|(i, tx)| {
if let Transaction::DkgCommitments(_, commitments, _) = tx {
(Participant::new((i + 1).try_into().unwrap()).unwrap(), commitments.clone())
} else {
panic!("txs had non-commitments");
}
})
.collect();
async fn new_processors(
key: &Zeroizing<<Ristretto as Ciphersuite>::F>,
spec: &TributarySpec,
tributary: &Tributary<MemDb, Transaction, LocalP2p>,
) -> (TributaryDb<MemDb>, MemProcessors) {
let mut scanner_db = TributaryDb(MemDb::new());
let processors = MemProcessors::new();
handle_new_blocks::<_, _, _, _, _, _, LocalP2p>(
&mut scanner_db,
key,
|_, _, _, _, _| async {
panic!("provided TX caused recognized_id to be called in new_processors")
},
&processors,
|_, _| async { panic!("test tried to publish a new Serai TX in new_processors") },
spec,
&tributary.reader(),
)
.await;
(scanner_db, processors)
}
2023-04-23 02:18:41 -04:00
// Instantiate a scanner and verify it has nothing to report
let (mut scanner_db, processors) = new_processors(&keys[0], &spec, &tributaries[0].1).await;
assert!(processors.0.read().await.is_empty());
2023-04-23 02:18:41 -04:00
// Publish the last commitment
let block_before_tx = tributaries[0].1.tip().await;
2023-04-23 02:18:41 -04:00
assert!(tributaries[0].1.add_transaction(txs[0].clone()).await);
wait_for_tx_inclusion(&tributaries[0].1, block_before_tx, txs[0].hash()).await;
2023-04-23 02:18:41 -04:00
sleep(Duration::from_secs(Tributary::<MemDb, Transaction, LocalP2p>::block_time().into())).await;
// Verify the scanner emits a KeyGen::Commitments message
handle_new_blocks::<_, _, _, _, _, _, LocalP2p>(
&mut scanner_db,
&keys[0],
|_, _, _, _, _| async {
panic!("provided TX caused recognized_id to be called after Commitments")
},
&processors,
|_, _| async { panic!("test tried to publish a new Serai TX after Commitments") },
&spec,
&tributaries[0].1.reader(),
)
.await;
{
let mut msgs = processors.0.write().await;
assert_eq!(msgs.len(), 1);
let msgs = msgs.get_mut(&spec.set().network).unwrap();
let mut expected_commitments = expected_commitments.clone();
expected_commitments.remove(&Participant::new((1).try_into().unwrap()).unwrap());
assert_eq!(
msgs.pop_front().unwrap(),
CoordinatorMessage::KeyGen(key_gen::CoordinatorMessage::Commitments {
id: KeyGenId { set: spec.set(), attempt: 0 },
commitments: expected_commitments
})
);
assert!(msgs.is_empty());
}
// Verify all keys exhibit this scanner behavior
for (i, key) in keys.iter().enumerate() {
let (_, processors) = new_processors(key, &spec, &tributaries[i].1).await;
let mut msgs = processors.0.write().await;
assert_eq!(msgs.len(), 1);
let msgs = msgs.get_mut(&spec.set().network).unwrap();
let mut expected_commitments = expected_commitments.clone();
expected_commitments.remove(&Participant::new((i + 1).try_into().unwrap()).unwrap());
assert_eq!(
msgs.pop_front().unwrap(),
CoordinatorMessage::KeyGen(key_gen::CoordinatorMessage::Commitments {
id: KeyGenId { set: spec.set(), attempt: 0 },
commitments: expected_commitments
})
);
2023-04-23 02:18:41 -04:00
assert!(msgs.is_empty());
}
// Now do shares
let mut txs = vec![];
for (k, key) in keys.iter().enumerate() {
2023-04-23 02:18:41 -04:00
let attempt = 0;
let mut shares = vec![];
2023-04-23 02:18:41 -04:00
for i in 0 .. keys.len() {
if i != k {
let mut share = vec![0; 256];
OsRng.fill_bytes(&mut share);
shares.push(share);
}
2023-04-23 02:18:41 -04:00
}
let mut tx = Transaction::DkgShares {
attempt,
shares,
confirmation_nonces: crate::tributary::dkg_confirmation_nonces(key, &spec, 0),
signed: Transaction::empty_signed(),
};
2023-04-23 02:18:41 -04:00
tx.sign(&mut OsRng, spec.genesis(), key, 1);
txs.push(tx);
}
let block_before_tx = tributaries[0].1.tip().await;
2023-04-23 02:18:41 -04:00
for (i, tx) in txs.iter().enumerate().skip(1) {
assert!(tributaries[i].1.add_transaction(tx.clone()).await);
}
for tx in txs.iter().skip(1) {
wait_for_tx_inclusion(&tributaries[0].1, block_before_tx, tx.hash()).await;
}
// With just 4 sets of shares, nothing should happen yet
handle_new_blocks::<_, _, _, _, _, _, LocalP2p>(
&mut scanner_db,
&keys[0],
|_, _, _, _, _| async {
panic!("provided TX caused recognized_id to be called after some shares")
},
&processors,
|_, _| async { panic!("test tried to publish a new Serai TX after some shares") },
&spec,
&tributaries[0].1.reader(),
)
.await;
assert_eq!(processors.0.read().await.len(), 1);
assert!(processors.0.read().await[&spec.set().network].is_empty());
2023-04-23 02:18:41 -04:00
// Publish the final set of shares
let block_before_tx = tributaries[0].1.tip().await;
2023-04-23 02:18:41 -04:00
assert!(tributaries[0].1.add_transaction(txs[0].clone()).await);
wait_for_tx_inclusion(&tributaries[0].1, block_before_tx, txs[0].hash()).await;
2023-04-23 02:18:41 -04:00
sleep(Duration::from_secs(Tributary::<MemDb, Transaction, LocalP2p>::block_time().into())).await;
// Each scanner should emit a distinct shares message
let shares_for = |i: usize| {
CoordinatorMessage::KeyGen(key_gen::CoordinatorMessage::Shares {
id: KeyGenId { set: spec.set(), attempt: 0 },
shares: txs
.iter()
.enumerate()
.filter_map(|(l, tx)| {
if let Transaction::DkgShares { shares, .. } = tx {
if i == l {
None
} else {
let relative_i = i - (if i > l { 1 } else { 0 });
Some((
Participant::new((l + 1).try_into().unwrap()).unwrap(),
shares[relative_i].clone(),
))
}
2023-04-23 02:18:41 -04:00
} else {
panic!("txs had non-shares");
}
})
.collect::<HashMap<_, _>>(),
})
};
// Any scanner which has handled the prior blocks should only emit the new event
handle_new_blocks::<_, _, _, _, _, _, LocalP2p>(
&mut scanner_db,
&keys[0],
|_, _, _, _, _| async { panic!("provided TX caused recognized_id to be called after shares") },
&processors,
|_, _| async { panic!("test tried to publish a new Serai TX") },
&spec,
&tributaries[0].1.reader(),
)
.await;
2023-04-23 02:18:41 -04:00
{
let mut msgs = processors.0.write().await;
assert_eq!(msgs.len(), 1);
let msgs = msgs.get_mut(&spec.set().network).unwrap();
2023-04-23 02:18:41 -04:00
assert_eq!(msgs.pop_front().unwrap(), shares_for(0));
assert!(msgs.is_empty());
}
// Yet new scanners should emit all events
for (i, key) in keys.iter().enumerate() {
let (_, processors) = new_processors(key, &spec, &tributaries[i].1).await;
let mut msgs = processors.0.write().await;
assert_eq!(msgs.len(), 1);
let msgs = msgs.get_mut(&spec.set().network).unwrap();
let mut expected_commitments = expected_commitments.clone();
expected_commitments.remove(&Participant::new((i + 1).try_into().unwrap()).unwrap());
assert_eq!(
msgs.pop_front().unwrap(),
CoordinatorMessage::KeyGen(key_gen::CoordinatorMessage::Commitments {
id: KeyGenId { set: spec.set(), attempt: 0 },
commitments: expected_commitments
})
);
2023-04-23 02:18:41 -04:00
assert_eq!(msgs.pop_front().unwrap(), shares_for(i));
assert!(msgs.is_empty());
}
// Send DkgConfirmed
let mut substrate_key = [0; 32];
OsRng.fill_bytes(&mut substrate_key);
let mut network_key = vec![0; usize::try_from((OsRng.next_u64() % 32) + 32).unwrap()];
OsRng.fill_bytes(&mut network_key);
let key_pair = (serai_client::Public(substrate_key), network_key.try_into().unwrap());
let mut txs = vec![];
2023-09-27 13:00:04 -04:00
for key in keys.iter() {
let attempt = 0;
// This is fine to re-use the one DB as such, due to exactly how this specific call is coded,
// albeit poor
let mut txn = scanner_db.0.txn();
let share =
crate::tributary::generated_key_pair::<MemDb>(&mut txn, key, &spec, &key_pair, 0).unwrap();
txn.commit();
let mut tx = Transaction::DkgConfirmed(attempt, share, Transaction::empty_signed());
tx.sign(&mut OsRng, spec.genesis(), key, 2);
txs.push(tx);
}
let block_before_tx = tributaries[0].1.tip().await;
for (i, tx) in txs.iter().enumerate() {
assert!(tributaries[i].1.add_transaction(tx.clone()).await);
}
for tx in txs.iter() {
wait_for_tx_inclusion(&tributaries[0].1, block_before_tx, tx.hash()).await;
}
// The scanner should successfully try to publish a transaction with a validly signed signature
handle_new_blocks::<_, _, _, _, _, _, LocalP2p>(
&mut scanner_db,
&keys[0],
|_, _, _, _, _| async {
panic!("provided TX caused recognized_id to be called after DKG confirmation")
},
&processors,
|set, tx| {
let spec = spec.clone();
let key_pair = key_pair.clone();
async move {
let tx = tx.0;
// Version, Pallet, Call, Network, Key Pair, Signature
let expected_len = 1 + 1 + 1 + 1 + 32 + 1 + key_pair.1.len() + 64;
// It's length prefixed
assert_eq!(tx.len(), 2 + expected_len);
let expected_len = u16::try_from(expected_len).unwrap();
// Check the encoded length
let bottom_six = expected_len & 0b111111;
let upper_eight = expected_len >> 6;
assert_eq!(u8::try_from((bottom_six << 2) | 1).unwrap(), tx[0]);
assert_eq!(u8::try_from(upper_eight).unwrap(), tx[1]);
// Version
assert_eq!(tx[2], 4);
// Pallet
// TODO
// Call
type Call = serai_client::runtime::validator_sets::Call<serai_client::runtime::Runtime>;
let tx = Call::decode(&mut &tx[4 ..]).unwrap();
match tx {
Call::set_keys { network, key_pair: set_key_pair, signature } => {
assert_eq!(set, spec.set());
assert_eq!(set.network, network);
assert_eq!(key_pair, set_key_pair);
assert!(signature.verify(
&*serai_client::validator_sets::primitives::set_keys_message(&set, &key_pair),
&serai_client::Public(
frost::dkg::musig::musig_key::<Ristretto>(
&serai_client::validator_sets::primitives::musig_context(set),
&spec
.validators()
.into_iter()
.map(|(validator, _)| validator)
.collect::<Vec<_>>()
)
.unwrap()
.to_bytes()
),
));
}
_ => panic!("Serai TX wasn't to set_keys"),
}
}
},
&spec,
&tributaries[0].1.reader(),
)
.await;
{
assert!(processors.0.read().await.get(&spec.set().network).unwrap().is_empty());
}
}