Merge bitcoin/bitcoin#24304: [kernel 0/n] Introduce `bitcoin-chainstate`

2c03cec2ff8cdbfd5da92bfb507d218e5c6435b0 ci: Build bitcoin-chainstate (Carl Dong)
095aa6ca37bf0bd5c5e221bab779978a99b2a34c build: Add example bitcoin-chainstate executable (Carl Dong)

Pull request description:

  Part of: #24303

  This PR introduces an example/demo `bitcoin-chainstate` executable using said library which can print out information about a datadir and take in new blocks on stdin.

  Please read the commit messages for more details.

  -----

  #### You may ask: WTF?! Why is `index/*.cpp`, etc. being linked in?

  This PR is meant only to capture the state of dependencies in our consensus engine as of right now. There are many things to decouple from consensus, which will be done in subsequent PRs. Listing the files out right now in `bitcoin_chainstate_SOURCES` is purely to give us a clear picture of the task at hand, it is **not** to say that these dependencies _belongs_ there in any way.

  ### TODO

  1. Clean up `bitcoin-chainstate.cpp`
     It is quite ugly, with a lot of comments I've left for myself, I should clean it up to the best of my abilities (the ugliness of our init/shutdown might be the upper bound on cleanliness here...)

ACKs for top commit:
  ajtowns:
    ACK 2c03cec2ff8cdbfd5da92bfb507d218e5c6435b0
  ryanofsky:
    Code review ACK 2c03cec2ff8cdbfd5da92bfb507d218e5c6435b0. Just rebase, comments, formatting change since last review
  MarcoFalke:
    re-ACK 2c03cec2ff8cdbfd5da92bfb507d218e5c6435b0 🏔

Tree-SHA512: 86e7fb5718caa577df8abc8288c754f4a590650d974df9d2f6476c87ed25c70f923c4db651c6963f33498fc7a3a31f6692b9a75cbc996bf4888c5dac2f34a13b

2 files changed, 362 insertions, 0 deletions

diff --git a/src/Makefile.am b/src/Makefile.am
index 417a611181..8f4cbee62f 100644
--- a/src/Makefile.am
+++ b/src/Makefile.am
@@ -106,6 +106,10 @@ if BUILD_BITCOIN_UTIL
   bin_PROGRAMS += bitcoin-util
 endif
 
+if BUILD_BITCOIN_CHAINSTATE
+  bin_PROGRAMS += bitcoin-chainstate
+endif
+
 .PHONY: FORCE check-symbols check-security
 # bitcoin core #
 BITCOIN_CORE_H = \
@@ -769,6 +773,102 @@ bitcoin_util_LDADD = \
   $(LIBSECP256K1)
 #
 
+# bitcoin-chainstate binary #
+bitcoin_chainstate_SOURCES = \
+  bitcoin-chainstate.cpp \
+  arith_uint256.cpp \
+  blockfilter.cpp \
+  chain.cpp \
+  chainparamsbase.cpp \
+  chainparams.cpp \
+  clientversion.cpp \
+  coins.cpp \
+  compat/glibcxx_sanity.cpp \
+  compressor.cpp \
+  consensus/merkle.cpp \
+  consensus/tx_check.cpp \
+  consensus/tx_verify.cpp \
+  core_read.cpp \
+  dbwrapper.cpp \
+  deploymentinfo.cpp \
+  deploymentstatus.cpp \
+  flatfile.cpp \
+  fs.cpp \
+  hash.cpp \
+  index/base.cpp \
+  index/blockfilterindex.cpp \
+  index/coinstatsindex.cpp \
+  init/common.cpp \
+  key.cpp \
+  logging.cpp \
+  netaddress.cpp \
+  node/blockstorage.cpp \
+  node/chainstate.cpp \
+  node/coinstats.cpp \
+  node/ui_interface.cpp \
+  policy/feerate.cpp \
+  policy/fees.cpp \
+  policy/packages.cpp \
+  policy/policy.cpp \
+  policy/rbf.cpp \
+  policy/settings.cpp \
+  pow.cpp \
+  primitives/block.cpp \
+  primitives/transaction.cpp \
+  pubkey.cpp \
+  random.cpp \
+  randomenv.cpp \
+  scheduler.cpp \
+  script/interpreter.cpp \
+  script/script.cpp \
+  script/script_error.cpp \
+  script/sigcache.cpp \
+  script/standard.cpp \
+  shutdown.cpp \
+  signet.cpp \
+  support/cleanse.cpp \
+  support/lockedpool.cpp \
+  sync.cpp \
+  threadinterrupt.cpp \
+  timedata.cpp \
+  txdb.cpp \
+  txmempool.cpp \
+  uint256.cpp \
+  util/asmap.cpp \
+  util/bytevectorhash.cpp \
+  util/getuniquepath.cpp \
+  util/hasher.cpp \
+  util/moneystr.cpp \
+  util/rbf.cpp \
+  util/serfloat.cpp \
+  util/settings.cpp \
+  util/strencodings.cpp \
+  util/syscall_sandbox.cpp \
+  util/system.cpp \
+  util/thread.cpp \
+  util/threadnames.cpp \
+  util/time.cpp \
+  util/tokenpipe.cpp \
+  validation.cpp \
+  validationinterface.cpp \
+  versionbits.cpp \
+  warnings.cpp
+bitcoin_chainstate_CPPFLAGS = $(AM_CPPFLAGS) $(BITCOIN_INCLUDES)
+bitcoin_chainstate_CXXFLAGS = $(AM_CXXFLAGS) $(PIE_FLAGS)
+bitcoin_chainstate_LDFLAGS = $(RELDFLAGS) $(AM_LDFLAGS) $(LIBTOOL_APP_LDFLAGS) $(PTHREAD_FLAGS)
+bitcoin_chainstate_LDADD = \
+  $(LIBBITCOIN_CRYPTO) \
+  $(LIBUNIVALUE) \
+  $(LIBSECP256K1) \
+  $(LIBLEVELDB) \
+  $(LIBLEVELDB_SSE42) \
+  $(LIBMEMENV)
+
+# Required for obj/build.h to be generated first.
+# More details: https://www.gnu.org/software/automake/manual/html_node/Built-Sources-Example.html
+bitcoin_chainstate-clientversion.$(OBJEXT): obj/build.h
+#
+
 # bitcoinconsensus library #
 if BUILD_BITCOIN_LIBS
 include_HEADERS = script/bitcoinconsensus.h
diff --git a/src/bitcoin-chainstate.cpp b/src/bitcoin-chainstate.cpp
new file mode 100644
index 0000000000..f93197350d
--- /dev/null
+++ b/src/bitcoin-chainstate.cpp
@@ -0,0 +1,262 @@
+// Copyright (c) 2022 The Bitcoin Core developers
+// Distributed under the MIT software license, see the accompanying
+// file COPYING or http://www.opensource.org/licenses/mit-license.php.
+//
+// The bitcoin-chainstate executable serves to surface the dependencies required
+// by a program wishing to use Bitcoin Core's consensus engine as it is right
+// now.
+//
+// DEVELOPER NOTE: Since this is a "demo-only", experimental, etc. executable,
+//                 it may diverge from Bitcoin Core's coding style.
+//
+// It is part of the libbitcoinkernel project.
+
+#include <chainparams.h>
+#include <consensus/validation.h>
+#include <core_io.h>
+#include <init/common.h>
+#include <node/blockstorage.h>
+#include <node/chainstate.h>
+#include <scheduler.h>
+#include <script/sigcache.h>
+#include <util/system.h>
+#include <util/thread.h>
+#include <validation.h>
+#include <validationinterface.h>
+
+#include <filesystem>
+#include <functional>
+#include <iosfwd>
+
+const std::function<std::string(const char*)> G_TRANSLATION_FUN = nullptr;
+
+int main(int argc, char* argv[])
+{
+    // SETUP: Argument parsing and handling
+    if (argc != 2) {
+        std::cerr
+            << "Usage: " << argv[0] << " DATADIR" << std::endl
+            << "Display DATADIR information, and process hex-encoded blocks on standard input." << std::endl
+            << std::endl
+            << "IMPORTANT: THIS EXECUTABLE IS EXPERIMENTAL, FOR TESTING ONLY, AND EXPECTED TO" << std::endl
+            << "           BREAK IN FUTURE VERSIONS. DO NOT USE ON YOUR ACTUAL DATADIR." << std::endl;
+        return 1;
+    }
+    std::filesystem::path abs_datadir = std::filesystem::absolute(argv[1]);
+    std::filesystem::create_directories(abs_datadir);
+    gArgs.ForceSetArg("-datadir", abs_datadir.string());
+
+
+    // SETUP: Misc Globals
+    SelectParams(CBaseChainParams::MAIN);
+    const CChainParams& chainparams = Params();
+
+    init::SetGlobals(); // ECC_Start, etc.
+
+    // Necessary for CheckInputScripts (eventually called by ProcessNewBlock),
+    // which will try the script cache first and fall back to actually
+    // performing the check with the signature cache.
+    InitSignatureCache();
+    InitScriptExecutionCache();
+
+
+    // SETUP: Scheduling and Background Signals
+    CScheduler scheduler{};
+    // Start the lightweight task scheduler thread
+    scheduler.m_service_thread = std::thread(util::TraceThread, "scheduler", [&] { scheduler.serviceQueue(); });
+
+    // Gather some entropy once per minute.
+    scheduler.scheduleEvery(RandAddPeriodic, std::chrono::minutes{1});
+
+    GetMainSignals().RegisterBackgroundSignalScheduler(scheduler);
+
+
+    // SETUP: Chainstate
+    ChainstateManager chainman;
+
+    auto rv = node::LoadChainstate(false,
+                                   std::ref(chainman),
+                                   nullptr,
+                                   false,
+                                   chainparams.GetConsensus(),
+                                   false,
+                                   2 << 20,
+                                   2 << 22,
+                                   (450 << 20) - (2 << 20) - (2 << 22),
+                                   false,
+                                   false,
+                                   []() { return false; });
+    if (rv.has_value()) {
+        std::cerr << "Failed to load Chain state from your datadir." << std::endl;
+        goto epilogue;
+    } else {
+        auto maybe_verify_error = node::VerifyLoadedChainstate(std::ref(chainman),
+                                                               false,
+                                                               false,
+                                                               chainparams.GetConsensus(),
+                                                               DEFAULT_CHECKBLOCKS,
+                                                               DEFAULT_CHECKLEVEL,
+                                                               /*get_unix_time_seconds=*/static_cast<int64_t (*)()>(GetTime));
+        if (maybe_verify_error.has_value()) {
+            std::cerr << "Failed to verify loaded Chain state from your datadir." << std::endl;
+            goto epilogue;
+        }
+    }
+
+    for (CChainState* chainstate : WITH_LOCK(::cs_main, return chainman.GetAll())) {
+        BlockValidationState state;
+        if (!chainstate->ActivateBestChain(state, nullptr)) {
+            std::cerr << "Failed to connect best block (" << state.ToString() << ")" << std::endl;
+            goto epilogue;
+        }
+    }
+
+    // Main program logic starts here
+    std::cout
+        << "Hello! I'm going to print out some information about your datadir." << std::endl
+        << "\t" << "Path: " << gArgs.GetDataDirNet() << std::endl
+        << "\t" << "Reindexing: " << std::boolalpha << node::fReindex.load() << std::noboolalpha << std::endl
+        << "\t" << "Snapshot Active: " << std::boolalpha << chainman.IsSnapshotActive() << std::noboolalpha << std::endl
+        << "\t" << "Active Height: " << chainman.ActiveHeight() << std::endl
+        << "\t" << "Active IBD: " << std::boolalpha << chainman.ActiveChainstate().IsInitialBlockDownload() << std::noboolalpha << std::endl;
+    {
+        CBlockIndex* tip = chainman.ActiveTip();
+        if (tip) {
+            std::cout << "\t" << tip->ToString() << std::endl;
+        }
+    }
+
+    for (std::string line; std::getline(std::cin, line);) {
+        if (line.empty()) {
+            std::cerr << "Empty line found" << std::endl;
+            break;
+        }
+
+        std::shared_ptr<CBlock> blockptr = std::make_shared<CBlock>();
+        CBlock& block = *blockptr;
+
+        if (!DecodeHexBlk(block, line)) {
+            std::cerr << "Block decode failed" << std::endl;
+            break;
+        }
+
+        if (block.vtx.empty() || !block.vtx[0]->IsCoinBase()) {
+            std::cerr << "Block does not start with a coinbase" << std::endl;
+            break;
+        }
+
+        uint256 hash = block.GetHash();
+        {
+            LOCK(cs_main);
+            const CBlockIndex* pindex = chainman.m_blockman.LookupBlockIndex(hash);
+            if (pindex) {
+                if (pindex->IsValid(BLOCK_VALID_SCRIPTS)) {
+                    std::cerr << "duplicate" << std::endl;
+                    break;
+                }
+                if (pindex->nStatus & BLOCK_FAILED_MASK) {
+                    std::cerr << "duplicate-invalid" << std::endl;
+                    break;
+                }
+            }
+        }
+
+        {
+            LOCK(cs_main);
+            const CBlockIndex* pindex = chainman.m_blockman.LookupBlockIndex(block.hashPrevBlock);
+            if (pindex) {
+                UpdateUncommittedBlockStructures(block, pindex, chainparams.GetConsensus());
+            }
+        }
+
+        // Adapted from rpc/mining.cpp
+        class submitblock_StateCatcher final : public CValidationInterface
+        {
+        public:
+            uint256 hash;
+            bool found;
+            BlockValidationState state;
+
+            explicit submitblock_StateCatcher(const uint256& hashIn) : hash(hashIn), found(false), state() {}
+
+        protected:
+            void BlockChecked(const CBlock& block, const BlockValidationState& stateIn) override
+            {
+                if (block.GetHash() != hash)
+                    return;
+                found = true;
+                state = stateIn;
+            }
+        };
+
+        bool new_block;
+        auto sc = std::make_shared<submitblock_StateCatcher>(block.GetHash());
+        RegisterSharedValidationInterface(sc);
+        bool accepted = chainman.ProcessNewBlock(chainparams, blockptr, /* force_processing */ true, /* new_block */ &new_block);
+        UnregisterSharedValidationInterface(sc);
+        if (!new_block && accepted) {
+            std::cerr << "duplicate" << std::endl;
+            break;
+        }
+        if (!sc->found) {
+            std::cerr << "inconclusive" << std::endl;
+            break;
+        }
+        std::cout << sc->state.ToString() << std::endl;
+        switch (sc->state.GetResult()) {
+        case BlockValidationResult::BLOCK_RESULT_UNSET:
+            std::cerr << "initial value. Block has not yet been rejected" << std::endl;
+            break;
+        case BlockValidationResult::BLOCK_CONSENSUS:
+            std::cerr << "invalid by consensus rules (excluding any below reasons)" << std::endl;
+            break;
+        case BlockValidationResult::BLOCK_RECENT_CONSENSUS_CHANGE:
+            std::cerr << "Invalid by a change to consensus rules more recent than SegWit." << std::endl;
+            break;
+        case BlockValidationResult::BLOCK_CACHED_INVALID:
+            std::cerr << "this block was cached as being invalid and we didn't store the reason why" << std::endl;
+            break;
+        case BlockValidationResult::BLOCK_INVALID_HEADER:
+            std::cerr << "invalid proof of work or time too old" << std::endl;
+            break;
+        case BlockValidationResult::BLOCK_MUTATED:
+            std::cerr << "the block's data didn't match the data committed to by the PoW" << std::endl;
+            break;
+        case BlockValidationResult::BLOCK_MISSING_PREV:
+            std::cerr << "We don't have the previous block the checked one is built on" << std::endl;
+            break;
+        case BlockValidationResult::BLOCK_INVALID_PREV:
+            std::cerr << "A block this one builds on is invalid" << std::endl;
+            break;
+        case BlockValidationResult::BLOCK_TIME_FUTURE:
+            std::cerr << "block timestamp was > 2 hours in the future (or our clock is bad)" << std::endl;
+            break;
+        case BlockValidationResult::BLOCK_CHECKPOINT:
+            std::cerr << "the block failed to meet one of our checkpoints" << std::endl;
+            break;
+        }
+    }
+
+epilogue:
+    // Without this precise shutdown sequence, there will be a lot of nullptr
+    // dereferencing and UB.
+    scheduler.stop();
+    if (chainman.m_load_block.joinable()) chainman.m_load_block.join();
+    StopScriptCheckWorkerThreads();
+
+    GetMainSignals().FlushBackgroundCallbacks();
+    {
+        LOCK(cs_main);
+        for (CChainState* chainstate : chainman.GetAll()) {
+            if (chainstate->CanFlushToDisk()) {
+                chainstate->ForceFlushStateToDisk();
+                chainstate->ResetCoinsViews();
+            }
+        }
+    }
+    GetMainSignals().UnregisterBackgroundSignalScheduler();
+
+    UnloadBlockIndex(nullptr, chainman);
+
+    init::UnsetGlobals();
+}