Merge #19328: Add gettxoutsetinfo hash_type option

40506bf93f955adfbc446c4d5fee4fa8bcfd7d9a test: Test gettxouttsetinfo hash_type option (Fabian Jahr)
f17a4d1c4ddce6935a353004898fb4e8618a213e rpc: Add hash_type NONE to gettxoutsetinfo (Fabian Jahr)
a712cf6f6801157667fcf36d1c498b6fff6d328a rpc: gettxoutsetinfo can specify hash_type (only legacy option for now) (Fabian Jahr)
605884ef21318fc3f326dbdf4901cb353ba63fab refactor: Extract GetBogoSize function (Fabian Jahr)

Pull request description:

  This is another intermediate part of the Coinstats Index (tracked in #18000).

  Sjors suggested [here](https://github.com/bitcoin/bitcoin/pull/18000#issuecomment-641423019) that the part of the changes in #19145 that don't rely on the new `hash_type` muhash, i.e. that are for `hash_type=none`, could be merged separately from everything involving muhash. So these changes are extracted from #19145 here and can be merged without any other requirements.

  Building the index with no UTXO set hash is still valuable because `gettxoutsetinfo` can still be used to audit the `total_amount` for example. By itself this PR is not a huge improvement, `hash_type=none` is speeding up `gettxoutsetinfo` by about 10%, but it enables the implementation of an index on top of it in a follow-up and that means large parts of the index code of Coinstats Index can be merged while reviews for the hashing algorithm might take longer.

ACKs for top commit:
  MarcoFalke:
    ACK 40506bf93f955adfbc446c4d5fee4fa8bcfd7d9a 🖨
  Sjors:
    tACK 40506bf93f955adfbc446c4d5fee4fa8bcfd7d9a

Tree-SHA512: 3964c2b8eed427511b1aa9b2ef285dff27dc4d1537d72c3911e435b6e6b40912232da4acb3a09bd19a0372ddffa44103388d8a650169d95a4a727b970d210add

2 files changed, 67 insertions, 11 deletions

diff --git a/src/node/coinstats.cpp b/src/node/coinstats.cpp
index e3c4c828b6..fb46ea1731 100644
--- a/src/node/coinstats.cpp
+++ b/src/node/coinstats.cpp
@@ -8,13 +8,23 @@
 #include <coins.h>
 #include <hash.h>
 #include <serialize.h>
-#include <validation.h>
 #include <uint256.h>
 #include <util/system.h>
+#include <validation.h>
 
 #include <map>
 
-static void ApplyStats(CCoinsStats &stats, CHashWriter& ss, const uint256& hash, const std::map<uint32_t, Coin>& outputs)
+static uint64_t GetBogoSize(const CScript& scriptPubKey)
+{
+    return 32 /* txid */ +
+           4 /* vout index */ +
+           4 /* height + coinbase */ +
+           8 /* amount */ +
+           2 /* scriptPubKey len */ +
+           scriptPubKey.size() /* scriptPubKey */;
+}
+
+static void ApplyStats(CCoinsStats& stats, CHashWriter& ss, const uint256& hash, const std::map<uint32_t, Coin>& outputs)
 {
     assert(!outputs.empty());
     ss << hash;
@@ -26,26 +36,38 @@ static void ApplyStats(CCoinsStats &stats, CHashWriter& ss, const uint256& hash,
         ss << VARINT_MODE(output.second.out.nValue, VarIntMode::NONNEGATIVE_SIGNED);
         stats.nTransactionOutputs++;
         stats.nTotalAmount += output.second.out.nValue;
-        stats.nBogoSize += 32 /* txid */ + 4 /* vout index */ + 4 /* height + coinbase */ + 8 /* amount */ +
-                           2 /* scriptPubKey len */ + output.second.out.scriptPubKey.size() /* scriptPubKey */;
+        stats.nBogoSize += GetBogoSize(output.second.out.scriptPubKey);
     }
     ss << VARINT(0u);
 }
 
+static void ApplyStats(CCoinsStats& stats, std::nullptr_t, const uint256& hash, const std::map<uint32_t, Coin>& outputs)
+{
+    assert(!outputs.empty());
+    stats.nTransactions++;
+    for (const auto& output : outputs) {
+        stats.nTransactionOutputs++;
+        stats.nTotalAmount += output.second.out.nValue;
+        stats.nBogoSize += GetBogoSize(output.second.out.scriptPubKey);
+    }
+}
+
 //! Calculate statistics about the unspent transaction output set
-bool GetUTXOStats(CCoinsView* view, CCoinsStats& stats, const std::function<void()>& interruption_point)
+template <typename T>
+static bool GetUTXOStats(CCoinsView* view, CCoinsStats& stats, T hash_obj, const std::function<void()>& interruption_point)
 {
     stats = CCoinsStats();
     std::unique_ptr<CCoinsViewCursor> pcursor(view->Cursor());
     assert(pcursor);
 
-    CHashWriter ss(SER_GETHASH, PROTOCOL_VERSION);
     stats.hashBlock = pcursor->GetBestBlock();
     {
         LOCK(cs_main);
         stats.nHeight = LookupBlockIndex(stats.hashBlock)->nHeight;
     }
-    ss << stats.hashBlock;
+
+    PrepareHash(hash_obj, stats);
+
     uint256 prevkey;
     std::map<uint32_t, Coin> outputs;
     while (pcursor->Valid()) {
@@ -54,7 +76,7 @@ bool GetUTXOStats(CCoinsView* view, CCoinsStats& stats, const std::function<void
         Coin coin;
         if (pcursor->GetKey(key) && pcursor->GetValue(coin)) {
             if (!outputs.empty() && key.hash != prevkey) {
-                ApplyStats(stats, ss, prevkey, outputs);
+                ApplyStats(stats, hash_obj, prevkey, outputs);
                 outputs.clear();
             }
             prevkey = key.hash;
@@ -66,9 +88,38 @@ bool GetUTXOStats(CCoinsView* view, CCoinsStats& stats, const std::function<void
         pcursor->Next();
     }
     if (!outputs.empty()) {
-        ApplyStats(stats, ss, prevkey, outputs);
+        ApplyStats(stats, hash_obj, prevkey, outputs);
     }
-    stats.hashSerialized = ss.GetHash();
+
+    FinalizeHash(hash_obj, stats);
+
     stats.nDiskSize = view->EstimateSize();
     return true;
 }
+
+bool GetUTXOStats(CCoinsView* view, CCoinsStats& stats, CoinStatsHashType hash_type, const std::function<void()>& interruption_point)
+{
+    switch (hash_type) {
+    case(CoinStatsHashType::HASH_SERIALIZED): {
+        CHashWriter ss(SER_GETHASH, PROTOCOL_VERSION);
+        return GetUTXOStats(view, stats, ss, interruption_point);
+    }
+    case(CoinStatsHashType::NONE): {
+        return GetUTXOStats(view, stats, nullptr, interruption_point);
+    }
+    } // no default case, so the compiler can warn about missing cases
+    assert(false);
+}
+
+// The legacy hash serializes the hashBlock
+static void PrepareHash(CHashWriter& ss, CCoinsStats& stats)
+{
+    ss << stats.hashBlock;
+}
+static void PrepareHash(std::nullptr_t, CCoinsStats& stats) {}
+
+static void FinalizeHash(CHashWriter& ss, CCoinsStats& stats)
+{
+    stats.hashSerialized = ss.GetHash();
+}
+static void FinalizeHash(std::nullptr_t, CCoinsStats& stats) {}
diff --git a/src/node/coinstats.h b/src/node/coinstats.h
index d9cdaa3036..2a7441c10e 100644
--- a/src/node/coinstats.h
+++ b/src/node/coinstats.h
@@ -14,6 +14,11 @@
 
 class CCoinsView;
 
+enum class CoinStatsHashType {
+    HASH_SERIALIZED,
+    NONE,
+};
+
 struct CCoinsStats
 {
     int nHeight{0};
@@ -30,6 +35,6 @@ struct CCoinsStats
 };
 
 //! Calculate statistics about the unspent transaction output set
-bool GetUTXOStats(CCoinsView* view, CCoinsStats& stats, const std::function<void()>& interruption_point = {});
+bool GetUTXOStats(CCoinsView* view, CCoinsStats& stats, const CoinStatsHashType hash_type, const std::function<void()>& interruption_point = {});
 
 #endif // BITCOIN_NODE_COINSTATS_H