Merge #21575: refactor: Create blockstorage module

fadcd3f78e1dd1acd7a774f8fad68dc471ff9e1f doc: Remove irrelevant link to GitHub (MarcoFalke)
fa121b628d51bb0e25eb3fbd716881fa55527dc7 blockstorage: [refactor] Use chainman reference where possible (MarcoFalke)
fa0c7d9ad24d3c9515d3f9c136af4071cbd79055 move-only: Move *Disk functions to blockstorage (MarcoFalke)
fa91b2b2b3447a3645e7958c7dc4e1946a69cb9c move-only: Move AbortNode to shutdown (MarcoFalke)
fa413f07a14744e7d7f7746e861aabd9cf938f61 move-only: Move ThreadImport to blockstorage (MarcoFalke)
faf843c07f99f91603e08ea858f972516f1d669a refactor: Move load block thread into ChainstateManager (MarcoFalke)

Pull request description:

  This picks up the closed pull request #21030 and is the first step toward fixing #21220.

  The basic idea is to move all disk access into a separate module with benefits:
  * Breaking down the massive files init.cpp and validation.cpp into logical units
  * Creating a standalone-module to reduce the mental complexity
  * Pave the way to fix validation related circular dependencies
  * Pave the way to mock disk access for testing, especially where it is performance critical (like fuzzing)

ACKs for top commit:
  promag:
    Code review ACK fadcd3f78e, checked (almost) moved only changes. This is a nice tidy up change and doesn't change behavior. Easily reviewed commit by commit.
  jamesob:
    ACK fadcd3f78e1dd1acd7a774f8fad68dc471ff9e1f ([`jamesob/ackr/21575.1.MarcoFalke.refactor_create_blocksto`](https://github.com/jamesob/bitcoin/tree/ackr/21575.1.MarcoFalke.refactor_create_blocksto))
  ryanofsky:
    Code review ACK fadcd3f78e1dd1acd7a774f8fad68dc471ff9e1f. New organization makes sense, moves extraneous things outside of validation.cpp. PR is also easy to review with helpfully split up moveonly commits.

Tree-SHA512: 917996592b6d8f9998289d8cb2b1b78b23d1fdb3b07216c9caec1380df33baa09dc2c1e706da669d440b497e79c9c62a01ca20dc202df5ad974a75f3ef7a143b

4 files changed, 288 insertions, 3 deletions

diff --git a/src/node/README.md b/src/node/README.md
index e99a717534..ab5979594d 100644
--- a/src/node/README.md
+++ b/src/node/README.md
@@ -15,8 +15,7 @@ As a rule of thumb, code in one of the [`src/node/`](./),
 calling code in the other directories directly, and only invoke it indirectly
 through the more limited [`src/interfaces/`](../interfaces/) classes.
 
-The [`src/node/`](./) directory is a new directory introduced in
-[#14978](https://github.com/bitcoin/bitcoin/pull/14978) and at the moment is
+This directory is at the moment
 sparsely populated. Eventually more substantial files like
 [`src/validation.cpp`](../validation.cpp) and
 [`src/txmempool.cpp`](../txmempool.cpp) might be moved there.
diff --git a/src/node/blockstorage.cpp b/src/node/blockstorage.cpp
new file mode 100644
index 0000000000..daed6605e8
--- /dev/null
+++ b/src/node/blockstorage.cpp
@@ -0,0 +1,244 @@
+// Copyright (c) 2011-2021 The Bitcoin Core developers
+// Distributed under the MIT software license, see the accompanying
+// file COPYING or http://www.opensource.org/licenses/mit-license.php.
+
+#include <node/blockstorage.h>
+
+#include <chain.h>
+#include <chainparams.h>
+#include <flatfile.h>
+#include <fs.h>
+#include <pow.h>
+#include <shutdown.h>
+#include <signet.h>
+#include <streams.h>
+#include <util/system.h>
+#include <validation.h>
+
+// From validation. TODO move here
+bool FindBlockPos(FlatFilePos& pos, unsigned int nAddSize, unsigned int nHeight, CChain& active_chain, uint64_t nTime, bool fKnown = false);
+
+static bool WriteBlockToDisk(const CBlock& block, FlatFilePos& pos, const CMessageHeader::MessageStartChars& messageStart)
+{
+    // Open history file to append
+    CAutoFile fileout(OpenBlockFile(pos), SER_DISK, CLIENT_VERSION);
+    if (fileout.IsNull()) {
+        return error("WriteBlockToDisk: OpenBlockFile failed");
+    }
+
+    // Write index header
+    unsigned int nSize = GetSerializeSize(block, fileout.GetVersion());
+    fileout << messageStart << nSize;
+
+    // Write block
+    long fileOutPos = ftell(fileout.Get());
+    if (fileOutPos < 0) {
+        return error("WriteBlockToDisk: ftell failed");
+    }
+    pos.nPos = (unsigned int)fileOutPos;
+    fileout << block;
+
+    return true;
+}
+
+bool ReadBlockFromDisk(CBlock& block, const FlatFilePos& pos, const Consensus::Params& consensusParams)
+{
+    block.SetNull();
+
+    // Open history file to read
+    CAutoFile filein(OpenBlockFile(pos, true), SER_DISK, CLIENT_VERSION);
+    if (filein.IsNull()) {
+        return error("ReadBlockFromDisk: OpenBlockFile failed for %s", pos.ToString());
+    }
+
+    // Read block
+    try {
+        filein >> block;
+    } catch (const std::exception& e) {
+        return error("%s: Deserialize or I/O error - %s at %s", __func__, e.what(), pos.ToString());
+    }
+
+    // Check the header
+    if (!CheckProofOfWork(block.GetHash(), block.nBits, consensusParams)) {
+        return error("ReadBlockFromDisk: Errors in block header at %s", pos.ToString());
+    }
+
+    // Signet only: check block solution
+    if (consensusParams.signet_blocks && !CheckSignetBlockSolution(block, consensusParams)) {
+        return error("ReadBlockFromDisk: Errors in block solution at %s", pos.ToString());
+    }
+
+    return true;
+}
+
+bool ReadBlockFromDisk(CBlock& block, const CBlockIndex* pindex, const Consensus::Params& consensusParams)
+{
+    FlatFilePos blockPos;
+    {
+        LOCK(cs_main);
+        blockPos = pindex->GetBlockPos();
+    }
+
+    if (!ReadBlockFromDisk(block, blockPos, consensusParams)) {
+        return false;
+    }
+    if (block.GetHash() != pindex->GetBlockHash()) {
+        return error("ReadBlockFromDisk(CBlock&, CBlockIndex*): GetHash() doesn't match index for %s at %s",
+                     pindex->ToString(), pindex->GetBlockPos().ToString());
+    }
+    return true;
+}
+
+bool ReadRawBlockFromDisk(std::vector<uint8_t>& block, const FlatFilePos& pos, const CMessageHeader::MessageStartChars& message_start)
+{
+    FlatFilePos hpos = pos;
+    hpos.nPos -= 8; // Seek back 8 bytes for meta header
+    CAutoFile filein(OpenBlockFile(hpos, true), SER_DISK, CLIENT_VERSION);
+    if (filein.IsNull()) {
+        return error("%s: OpenBlockFile failed for %s", __func__, pos.ToString());
+    }
+
+    try {
+        CMessageHeader::MessageStartChars blk_start;
+        unsigned int blk_size;
+
+        filein >> blk_start >> blk_size;
+
+        if (memcmp(blk_start, message_start, CMessageHeader::MESSAGE_START_SIZE)) {
+            return error("%s: Block magic mismatch for %s: %s versus expected %s", __func__, pos.ToString(),
+                         HexStr(blk_start),
+                         HexStr(message_start));
+        }
+
+        if (blk_size > MAX_SIZE) {
+            return error("%s: Block data is larger than maximum deserialization size for %s: %s versus %s", __func__, pos.ToString(),
+                         blk_size, MAX_SIZE);
+        }
+
+        block.resize(blk_size); // Zeroing of memory is intentional here
+        filein.read((char*)block.data(), blk_size);
+    } catch (const std::exception& e) {
+        return error("%s: Read from block file failed: %s for %s", __func__, e.what(), pos.ToString());
+    }
+
+    return true;
+}
+
+bool ReadRawBlockFromDisk(std::vector<uint8_t>& block, const CBlockIndex* pindex, const CMessageHeader::MessageStartChars& message_start)
+{
+    FlatFilePos block_pos;
+    {
+        LOCK(cs_main);
+        block_pos = pindex->GetBlockPos();
+    }
+
+    return ReadRawBlockFromDisk(block, block_pos, message_start);
+}
+
+/** Store block on disk. If dbp is non-nullptr, the file is known to already reside on disk */
+FlatFilePos SaveBlockToDisk(const CBlock& block, int nHeight, CChain& active_chain, const CChainParams& chainparams, const FlatFilePos* dbp)
+{
+    unsigned int nBlockSize = ::GetSerializeSize(block, CLIENT_VERSION);
+    FlatFilePos blockPos;
+    if (dbp != nullptr) {
+        blockPos = *dbp;
+    }
+    if (!FindBlockPos(blockPos, nBlockSize + 8, nHeight, active_chain, block.GetBlockTime(), dbp != nullptr)) {
+        error("%s: FindBlockPos failed", __func__);
+        return FlatFilePos();
+    }
+    if (dbp == nullptr) {
+        if (!WriteBlockToDisk(block, blockPos, chainparams.MessageStart())) {
+            AbortNode("Failed to write block");
+            return FlatFilePos();
+        }
+    }
+    return blockPos;
+}
+
+struct CImportingNow {
+    CImportingNow()
+    {
+        assert(fImporting == false);
+        fImporting = true;
+    }
+
+    ~CImportingNow()
+    {
+        assert(fImporting == true);
+        fImporting = false;
+    }
+};
+
+void ThreadImport(ChainstateManager& chainman, std::vector<fs::path> vImportFiles, const ArgsManager& args)
+{
+    const CChainParams& chainparams = Params();
+    ScheduleBatchPriority();
+
+    {
+        CImportingNow imp;
+
+        // -reindex
+        if (fReindex) {
+            int nFile = 0;
+            while (true) {
+                FlatFilePos pos(nFile, 0);
+                if (!fs::exists(GetBlockPosFilename(pos))) {
+                    break; // No block files left to reindex
+                }
+                FILE* file = OpenBlockFile(pos, true);
+                if (!file) {
+                    break; // This error is logged in OpenBlockFile
+                }
+                LogPrintf("Reindexing block file blk%05u.dat...\n", (unsigned int)nFile);
+                chainman.ActiveChainstate().LoadExternalBlockFile(chainparams, file, &pos);
+                if (ShutdownRequested()) {
+                    LogPrintf("Shutdown requested. Exit %s\n", __func__);
+                    return;
+                }
+                nFile++;
+            }
+            pblocktree->WriteReindexing(false);
+            fReindex = false;
+            LogPrintf("Reindexing finished\n");
+            // To avoid ending up in a situation without genesis block, re-try initializing (no-op if reindexing worked):
+            chainman.ActiveChainstate().LoadGenesisBlock(chainparams);
+        }
+
+        // -loadblock=
+        for (const fs::path& path : vImportFiles) {
+            FILE* file = fsbridge::fopen(path, "rb");
+            if (file) {
+                LogPrintf("Importing blocks file %s...\n", path.string());
+                chainman.ActiveChainstate().LoadExternalBlockFile(chainparams, file);
+                if (ShutdownRequested()) {
+                    LogPrintf("Shutdown requested. Exit %s\n", __func__);
+                    return;
+                }
+            } else {
+                LogPrintf("Warning: Could not open blocks file %s\n", path.string());
+            }
+        }
+
+        // scan for better chains in the block chain database, that are not yet connected in the active best chain
+
+        // We can't hold cs_main during ActivateBestChain even though we're accessing
+        // the chainman unique_ptrs since ABC requires us not to be holding cs_main, so retrieve
+        // the relevant pointers before the ABC call.
+        for (CChainState* chainstate : WITH_LOCK(::cs_main, return chainman.GetAll())) {
+            BlockValidationState state;
+            if (!chainstate->ActivateBestChain(state, chainparams, nullptr)) {
+                LogPrintf("Failed to connect best block (%s)\n", state.ToString());
+                StartShutdown();
+                return;
+            }
+        }
+
+        if (args.GetBoolArg("-stopafterblockimport", DEFAULT_STOPAFTERBLOCKIMPORT)) {
+            LogPrintf("Stopping after block import\n");
+            StartShutdown();
+            return;
+        }
+    } // End scope of CImportingNow
+    chainman.ActiveChainstate().LoadMempool(args);
+}
diff --git a/src/node/blockstorage.h b/src/node/blockstorage.h
new file mode 100644
index 0000000000..3b546f0719
--- /dev/null
+++ b/src/node/blockstorage.h
@@ -0,0 +1,40 @@
+// Copyright (c) 2011-2021 The Bitcoin Core developers
+// Distributed under the MIT software license, see the accompanying
+// file COPYING or http://www.opensource.org/licenses/mit-license.php.
+
+#ifndef BITCOIN_NODE_BLOCKSTORAGE_H
+#define BITCOIN_NODE_BLOCKSTORAGE_H
+
+#include <cstdint>
+#include <vector>
+
+#include <fs.h>
+#include <protocol.h> // For CMessageHeader::MessageStartChars
+
+class ArgsManager;
+class CBlock;
+class CBlockIndex;
+class CBlockUndo;
+class CChain;
+class CChainParams;
+class ChainstateManager;
+struct FlatFilePos;
+namespace Consensus {
+struct Params;
+}
+
+static constexpr bool DEFAULT_STOPAFTERBLOCKIMPORT{false};
+
+/** Functions for disk access for blocks */
+bool ReadBlockFromDisk(CBlock& block, const FlatFilePos& pos, const Consensus::Params& consensusParams);
+bool ReadBlockFromDisk(CBlock& block, const CBlockIndex* pindex, const Consensus::Params& consensusParams);
+bool ReadRawBlockFromDisk(std::vector<uint8_t>& block, const FlatFilePos& pos, const CMessageHeader::MessageStartChars& message_start);
+bool ReadRawBlockFromDisk(std::vector<uint8_t>& block, const CBlockIndex* pindex, const CMessageHeader::MessageStartChars& message_start);
+
+bool UndoReadFromDisk(CBlockUndo& blockundo, const CBlockIndex* pindex);
+
+FlatFilePos SaveBlockToDisk(const CBlock& block, int nHeight, CChain& active_chain, const CChainParams& chainparams, const FlatFilePos* dbp);
+
+void ThreadImport(ChainstateManager& chainman, std::vector<fs::path> vImportFiles, const ArgsManager& args);
+
+#endif // BITCOIN_NODE_BLOCKSTORAGE_H
diff --git a/src/node/interfaces.cpp b/src/node/interfaces.cpp
index e10e89b8cf..8befbf5e30 100644
--- a/src/node/interfaces.cpp
+++ b/src/node/interfaces.cpp
@@ -4,7 +4,6 @@
 
 #include <addrdb.h>
 #include <banman.h>
-#include <boost/signals2/signal.hpp>
 #include <chain.h>
 #include <chainparams.h>
 #include <init.h>
@@ -17,6 +16,7 @@
 #include <net_processing.h>
 #include <netaddress.h>
 #include <netbase.h>
+#include <node/blockstorage.h>
 #include <node/coin.h>
 #include <node/context.h>
 #include <node/transaction.h>
@@ -53,6 +53,8 @@
 #include <optional>
 #include <utility>
 
+#include <boost/signals2/signal.hpp>
+
 using interfaces::BlockTip;
 using interfaces::Chain;
 using interfaces::FoundBlock;