cmd, core, miner: rework genesis setup (ethereum#30907)

This pull request refactors the genesis setup function, the major
changes are highlighted here:

**(a) Triedb is opened in verkle mode if `EnableVerkleAtGenesis` is
configured in chainConfig or the database has been initialized previously with
`EnableVerkleAtGenesis` configured**.

A new config field `EnableVerkleAtGenesis` has been added in the
chainConfig. This field must be configured with True if Geth wants to initialize 
the genesis in Verkle mode.

In the verkle devnet-7, the verkle transition is activated at genesis.
Therefore, the verkle rules should be used since the genesis. In production
networks (mainnet and public testnets), verkle activation always occurs after
the genesis block. Therefore, this flag is only made for devnet and should be
deprecated later. Besides, verkle transition at non-genesis block hasn't been
implemented yet, it should be done in the following PRs.

**(b) The genesis initialization condition has been simplified**
There is a special mode supported by the Geth is that: Geth can be
initialized with an existing chain segment, which can fasten the node sync
process by retaining the chain freezer folder.

Originally, if the triedb is regarded as uninitialized and the genesis block can
be found in the chain freezer, the genesis block along with genesis state will be
committed. This condition has been simplified to checking the presence of chain
config in key-value store. The existence of chain config can represent the genesis
has been committed.

cmd/geth/chaincmd.go

@@ -230,11 +230,10 @@ func initGenesis(ctx *cli.Context) error {
 	triedb := utils.MakeTrieDatabase(ctx, chaindb, ctx.Bool(utils.CachePreimagesFlag.Name), false, genesis.IsVerkle())
 	defer triedb.Close()
 
-	_, hash, err := core.SetupGenesisBlockWithOverride(chaindb, triedb, genesis, &overrides)
+	_, hash, _, err := core.SetupGenesisBlockWithOverride(chaindb, triedb, genesis, &overrides)
 	if err != nil {
 		utils.Fatalf("Failed to write genesis block: %v", err)
 	}
-
 	log.Info("Successfully wrote genesis state", "database", "chaindata", "hash", hash)
 
 	return nil

cmd/utils/history_test.go

@@ -170,7 +170,7 @@ func TestHistoryImportAndExport(t *testing.T) {
 		db2.Close()
 	})
 
-	genesis.MustCommit(db2, triedb.NewDatabase(db, triedb.HashDefaults))
+	genesis.MustCommit(db2, triedb.NewDatabase(db2, triedb.HashDefaults))
 	imported, err := core.NewBlockChain(db2, nil, genesis, nil, ethash.NewFaker(), vm.Config{}, nil)
 	if err != nil {
 		t.Fatalf("unable to initialize chain: %v", err)

core/blockchain.go

@@ -269,14 +269,19 @@ func NewBlockChain(db ethdb.Database, cacheConfig *CacheConfig, genesis *Genesis
 		cacheConfig = defaultCacheConfig
 	}
 	// Open trie database with provided config
-	triedb := triedb.NewDatabase(db, cacheConfig.triedbConfig(genesis != nil && genesis.IsVerkle()))
+	enableVerkle, err := EnableVerkleAtGenesis(db, genesis)
+	if err != nil {
+		return nil, err
+	}
+	triedb := triedb.NewDatabase(db, cacheConfig.triedbConfig(enableVerkle))
 
-	// Setup the genesis block, commit the provided genesis specification
-	// to database if the genesis block is not present yet, or load the
-	// stored one from database.
-	chainConfig, genesisHash, genesisErr := SetupGenesisBlockWithOverride(db, triedb, genesis, overrides)
-	if _, ok := genesisErr.(*params.ConfigCompatError); genesisErr != nil && !ok {
-		return nil, genesisErr
+	// Write the supplied genesis to the database if it has not been initialized
+	// yet. The corresponding chain config will be returned, either from the
+	// provided genesis or from the locally stored configuration if the genesis
+	// has already been initialized.
+	chainConfig, genesisHash, compatErr, err := SetupGenesisBlockWithOverride(db, triedb, genesis, overrides)
+	if err != nil {
+		return nil, err
 	}
 	log.Info("")
 	log.Info(strings.Repeat("-", 153))
@@ -303,7 +308,6 @@ func NewBlockChain(db ethdb.Database, cacheConfig *CacheConfig, genesis *Genesis
 		vmConfig:      vmConfig,
 		logger:        vmConfig.Tracer,
 	}
-	var err error
 	bc.hc, err = NewHeaderChain(db, chainConfig, engine, bc.insertStopped)
 	if err != nil {
 		return nil, err
@@ -453,16 +457,15 @@ func NewBlockChain(db ethdb.Database, cacheConfig *CacheConfig, genesis *Genesis
 	}
 
 	// Rewind the chain in case of an incompatible config upgrade.
-	if compat, ok := genesisErr.(*params.ConfigCompatError); ok {
-		log.Warn("Rewinding chain to upgrade configuration", "err", compat)
-		if compat.RewindToTime > 0 {
-			bc.SetHeadWithTimestamp(compat.RewindToTime)
+	if compatErr != nil {
+		log.Warn("Rewinding chain to upgrade configuration", "err", compatErr)
+		if compatErr.RewindToTime > 0 {
+			bc.SetHeadWithTimestamp(compatErr.RewindToTime)
 		} else {
-			bc.SetHead(compat.RewindToBlock)
+			bc.SetHead(compatErr.RewindToBlock)
 		}
 		rawdb.WriteChainConfig(db, genesisHash, chainConfig)
 	}
-
 	// Start tx indexer if it's enabled.
 	if txLookupLimit != nil {
 		bc.txIndexer = newTxIndexer(*txLookupLimit, bc)

core/genesis.go

@@ -247,6 +247,24 @@ type ChainOverrides struct {
 	OverrideVerkle *uint64
 }
 
+// apply applies the chain overrides on the supplied chain config.
+func (o *ChainOverrides) apply(cfg *params.ChainConfig) (*params.ChainConfig, error) {
+	if o == nil || cfg == nil {
+		return cfg, nil
+	}
+	cpy := *cfg
+	if o.OverrideCancun != nil {
+		cpy.CancunTime = o.OverrideCancun
+	}
+	if o.OverrideVerkle != nil {
+		cpy.VerkleTime = o.OverrideVerkle
+	}
+	if err := cpy.CheckConfigForkOrder(); err != nil {
+		return nil, err
+	}
+	return &cpy, nil
+}
+
 // SetupGenesisBlock writes or updates the genesis block in db.
 // The block that will be used is:
 //
@@ -258,109 +276,102 @@ type ChainOverrides struct {
 // The stored chain configuration will be updated if it is compatible (i.e. does not
 // specify a fork block below the local head block). In case of a conflict, the
 // error is a *params.ConfigCompatError and the new, unwritten config is returned.
-//
-// The returned chain configuration is never nil.
-func SetupGenesisBlock(db ethdb.Database, triedb *triedb.Database, genesis *Genesis) (*params.ChainConfig, common.Hash, error) {
+func SetupGenesisBlock(db ethdb.Database, triedb *triedb.Database, genesis *Genesis) (*params.ChainConfig, common.Hash, *params.ConfigCompatError, error) {
 	return SetupGenesisBlockWithOverride(db, triedb, genesis, nil)
 }
 
-func SetupGenesisBlockWithOverride(db ethdb.Database, triedb *triedb.Database, genesis *Genesis, overrides *ChainOverrides) (*params.ChainConfig, common.Hash, error) {
+func SetupGenesisBlockWithOverride(db ethdb.Database, triedb *triedb.Database, genesis *Genesis, overrides *ChainOverrides) (*params.ChainConfig, common.Hash, *params.ConfigCompatError, error) {
+	// Sanitize the supplied genesis, ensuring it has the associated chain
+	// config attached.
 	if genesis != nil && genesis.Config == nil {
-		return params.AllEthashProtocolChanges, common.Hash{}, errGenesisNoConfig
-	}
-	applyOverrides := func(config *params.ChainConfig) {
-		if config != nil {
-			if overrides != nil && overrides.OverrideCancun != nil {
-				config.CancunTime = overrides.OverrideCancun
-			}
-			if overrides != nil && overrides.OverrideVerkle != nil {
-				config.VerkleTime = overrides.OverrideVerkle
-			}
-		}
+		return nil, common.Hash{}, nil, errGenesisNoConfig
 	}
-	// Just commit the new block if there is no stored genesis block.
-	stored := rawdb.ReadCanonicalHash(db, 0)
-	if (stored == common.Hash{}) {
+	// Commit the genesis if the database is empty
+	ghash := rawdb.ReadCanonicalHash(db, 0)
+	if (ghash == common.Hash{}) {
 		if genesis == nil {
 			log.Info("Writing default main-net genesis block")
 			genesis = DefaultGenesisBlock()
 		} else {
 			log.Info("Writing custom genesis block")
 		}
+		chainCfg, err := overrides.apply(genesis.Config)
+		if err != nil {
+			return nil, common.Hash{}, nil, err
+		}
+		genesis.Config = chainCfg
 
-		applyOverrides(genesis.Config)
 		block, err := genesis.Commit(db, triedb)
 		if err != nil {
-			return genesis.Config, common.Hash{}, err
+			return nil, common.Hash{}, nil, err
 		}
-		return genesis.Config, block.Hash(), nil
-	}
-	// The genesis block is present(perhaps in ancient database) while the
-	// state database is not initialized yet. It can happen that the node
-	// is initialized with an external ancient store. Commit genesis state
-	// in this case.
-	header := rawdb.ReadHeader(db, stored, 0)
-	if header.Root != types.EmptyRootHash && !triedb.Initialized(header.Root) {
+		return chainCfg, block.Hash(), nil, nil
+	}
+	// Commit the genesis if the genesis block exists in the ancient database
+	// but the key-value database is empty without initializing the genesis
+	// fields. This scenario can occur when the node is created from scratch
+	// with an existing ancient store.
+	storedCfg := rawdb.ReadChainConfig(db, ghash)
+	if storedCfg == nil {
+		// Ensure the stored genesis block matches with the given genesis. Private
+		// networks must explicitly specify the genesis in the config file, mainnet
+		// genesis will be used as default and the initialization will always fail.
 		if genesis == nil {
+			log.Info("Writing default main-net genesis block")
 			genesis = DefaultGenesisBlock()
+		} else {
+			log.Info("Writing custom genesis block")
 		}
-		applyOverrides(genesis.Config)
-		// Ensure the stored genesis matches with the given one.
-		hash := genesis.ToBlock().Hash()
-		if hash != stored {
-			return genesis.Config, hash, &GenesisMismatchError{stored, hash}
+		chainCfg, err := overrides.apply(genesis.Config)
+		if err != nil {
+			return nil, common.Hash{}, nil, err
+		}
+		genesis.Config = chainCfg
+
+		if hash := genesis.ToBlock().Hash(); hash != ghash {
+			return nil, common.Hash{}, nil, &GenesisMismatchError{ghash, hash}
 		}
 		block, err := genesis.Commit(db, triedb)
 		if err != nil {
-			return genesis.Config, hash, err
+			return nil, common.Hash{}, nil, err
 		}
-		return genesis.Config, block.Hash(), nil
+		return chainCfg, block.Hash(), nil, nil
 	}
-	// Check whether the genesis block is already written.
+	// The genesis block has already been committed previously. Verify that the
+	// provided genesis with chain overrides matches the existing one, and update
+	// the stored chain config if necessary.
 	if genesis != nil {
-		applyOverrides(genesis.Config)
-		hash := genesis.ToBlock().Hash()
-		if hash != stored {
-			return genesis.Config, hash, &GenesisMismatchError{stored, hash}
+		chainCfg, err := overrides.apply(genesis.Config)
+		if err != nil {
+			return nil, common.Hash{}, nil, err
+		}
+		genesis.Config = chainCfg
+
+		if hash := genesis.ToBlock().Hash(); hash != ghash {
+			return nil, common.Hash{}, nil, &GenesisMismatchError{ghash, hash}
 		}
-	}
-	// Get the existing chain configuration.
-	newcfg := genesis.configOrDefault(stored)
-	applyOverrides(newcfg)
-	if err := newcfg.CheckConfigForkOrder(); err != nil {
-		return newcfg, common.Hash{}, err
-	}
-	storedcfg := rawdb.ReadChainConfig(db, stored)
-	if storedcfg == nil {
-		log.Warn("Found genesis block without chain config")
-		rawdb.WriteChainConfig(db, stored, newcfg)
-		return newcfg, stored, nil
-	}
-	storedData, _ := json.Marshal(storedcfg)
-	// Special case: if a private network is being used (no genesis and also no
-	// mainnet hash in the database), we must not apply the `configOrDefault`
-	// chain config as that would be AllProtocolChanges (applying any new fork
-	// on top of an existing private network genesis block). In that case, only
-	// apply the overrides.
-	if genesis == nil && stored != params.MainnetGenesisHash {
-		newcfg = storedcfg
-		applyOverrides(newcfg)
 	}
 	// Check config compatibility and write the config. Compatibility errors
 	// are returned to the caller unless we're already at block zero.
 	head := rawdb.ReadHeadHeader(db)
 	if head == nil {
-		return newcfg, stored, errors.New("missing head header")
+		return nil, common.Hash{}, nil, errors.New("missing head header")
 	}
-	compatErr := storedcfg.CheckCompatible(newcfg, head.Number.Uint64(), head.Time)
+	newCfg := genesis.chainConfigOrDefault(ghash, storedCfg)
+
+	// TODO(rjl493456442) better to define the comparator of chain config
+	// and short circuit if the chain config is not changed.
+	compatErr := storedCfg.CheckCompatible(newCfg, head.Number.Uint64(), head.Time)
 	if compatErr != nil && ((head.Number.Uint64() != 0 && compatErr.RewindToBlock != 0) || (head.Time != 0 && compatErr.RewindToTime != 0)) {
-		return newcfg, stored, compatErr
+		return newCfg, ghash, compatErr, nil
 	}
-	// Don't overwrite if the old is identical to the new
-	if newData, _ := json.Marshal(newcfg); !bytes.Equal(storedData, newData) {
-		rawdb.WriteChainConfig(db, stored, newcfg)
+	// Don't overwrite if the old is identical to the new. It's useful
+	// for the scenarios that database is opened in the read-only mode.
+	storedData, _ := json.Marshal(storedCfg)
+	if newData, _ := json.Marshal(newCfg); !bytes.Equal(storedData, newData) {
+		rawdb.WriteChainConfig(db, ghash, newCfg)
 	}
-	return newcfg, stored, nil
+	return newCfg, ghash, nil, nil
 }
 
 // LoadChainConfig loads the stored chain config if it is already present in
@@ -396,7 +407,10 @@ func LoadChainConfig(db ethdb.Database, genesis *Genesis) (*params.ChainConfig,
 	return params.MainnetChainConfig, nil
 }
 
-func (g *Genesis) configOrDefault(ghash common.Hash) *params.ChainConfig {
+// chainConfigOrDefault retrieves the attached chain configuration. If the genesis
+// object is null, it returns the default chain configuration based on the given
+// genesis hash, or the locally stored config if it's not a pre-defined network.
+func (g *Genesis) chainConfigOrDefault(ghash common.Hash, stored *params.ChainConfig) *params.ChainConfig {
 	switch {
 	case g != nil:
 		return g.Config
@@ -407,14 +421,14 @@ func (g *Genesis) configOrDefault(ghash common.Hash) *params.ChainConfig {
 	case ghash == params.SepoliaGenesisHash:
 		return params.SepoliaChainConfig
 	default:
-		return params.AllEthashProtocolChanges
+		return stored
 	}
 }
 
 // IsVerkle indicates whether the state is already stored in a verkle
 // tree at genesis time.
 func (g *Genesis) IsVerkle() bool {
-	return g.Config.IsVerkle(new(big.Int).SetUint64(g.Number), g.Timestamp)
+	return g.Config.IsVerkleGenesis()
 }
 
 // ToBlock returns the genesis block according to genesis specification.
@@ -494,7 +508,7 @@ func (g *Genesis) Commit(db ethdb.Database, triedb *triedb.Database) (*types.Blo
 	}
 	config := g.Config
 	if config == nil {
-		config = params.AllEthashProtocolChanges
+		return nil, errors.New("invalid genesis without chain config")
 	}
 	if err := config.CheckConfigForkOrder(); err != nil {
 		return nil, err
@@ -514,16 +528,17 @@ func (g *Genesis) Commit(db ethdb.Database, triedb *triedb.Database) (*types.Blo
 	if err != nil {
 		return nil, err
 	}
-	rawdb.WriteGenesisStateSpec(db, block.Hash(), blob)
-	rawdb.WriteTd(db, block.Hash(), block.NumberU64(), block.Difficulty())
-	rawdb.WriteBlock(db, block)
-	rawdb.WriteReceipts(db, block.Hash(), block.NumberU64(), nil)
-	rawdb.WriteCanonicalHash(db, block.Hash(), block.NumberU64())
-	rawdb.WriteHeadBlockHash(db, block.Hash())
-	rawdb.WriteHeadFastBlockHash(db, block.Hash())
-	rawdb.WriteHeadHeaderHash(db, block.Hash())
-	rawdb.WriteChainConfig(db, block.Hash(), config)
-	return block, nil
+	batch := db.NewBatch()
+	rawdb.WriteGenesisStateSpec(batch, block.Hash(), blob)
+	rawdb.WriteTd(batch, block.Hash(), block.NumberU64(), block.Difficulty())
+	rawdb.WriteBlock(batch, block)
+	rawdb.WriteReceipts(batch, block.Hash(), block.NumberU64(), nil)
+	rawdb.WriteCanonicalHash(batch, block.Hash(), block.NumberU64())
+	rawdb.WriteHeadBlockHash(batch, block.Hash())
+	rawdb.WriteHeadFastBlockHash(batch, block.Hash())
+	rawdb.WriteHeadHeaderHash(batch, block.Hash())
+	rawdb.WriteChainConfig(batch, block.Hash(), config)
+	return block, batch.Write()
 }
 
 // MustCommit writes the genesis block and state to db, panicking on error.
@@ -536,6 +551,29 @@ func (g *Genesis) MustCommit(db ethdb.Database, triedb *triedb.Database) *types.
 	return block
 }
 
+// EnableVerkleAtGenesis indicates whether the verkle fork should be activated
+// at genesis. This is a temporary solution only for verkle devnet testing, where
+// verkle fork is activated at genesis, and the configured activation date has
+// already passed.
+//
+// In production networks (mainnet and public testnets), verkle activation always
+// occurs after the genesis block, making this function irrelevant in those cases.
+func EnableVerkleAtGenesis(db ethdb.Database, genesis *Genesis) (bool, error) {
+	if genesis != nil {
+		if genesis.Config == nil {
+			return false, errGenesisNoConfig
+		}
+		return genesis.Config.EnableVerkleAtGenesis, nil
+	}
+	if ghash := rawdb.ReadCanonicalHash(db, 0); ghash != (common.Hash{}) {
+		chainCfg := rawdb.ReadChainConfig(db, ghash)
+		if chainCfg != nil {
+			return chainCfg.EnableVerkleAtGenesis, nil
+		}
+	}
+	return false, nil
+}
+
 // DefaultGenesisBlock returns the Ethereum main net genesis block.
 func DefaultGenesisBlock() *Genesis {
 	return &Genesis{