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

3 files changed, 32 insertions, 6 deletions

diff --git a/src/rpc/blockchain.cpp b/src/rpc/blockchain.cpp
index 630a8b463f..98d4b2ce81 100644
--- a/src/rpc/blockchain.cpp
+++ b/src/rpc/blockchain.cpp
@@ -975,7 +975,9 @@ static UniValue gettxoutsetinfo(const JSONRPCRequest& request)
             RPCHelpMan{"gettxoutsetinfo",
                 "\nReturns statistics about the unspent transaction output set.\n"
                 "Note this call may take some time.\n",
-                {},
+                {
+                    {"hash_type", RPCArg::Type::STR, /* default */ "hash_serialized_2", "Which UTXO set hash should be calculated. Options: 'hash_serialized_2' (the legacy algorithm), 'none'."},
+                },
                 RPCResult{
                     RPCResult::Type::OBJ, "", "",
                     {
@@ -984,7 +986,7 @@ static UniValue gettxoutsetinfo(const JSONRPCRequest& request)
                         {RPCResult::Type::NUM, "transactions", "The number of transactions with unspent outputs"},
                         {RPCResult::Type::NUM, "txouts", "The number of unspent transaction outputs"},
                         {RPCResult::Type::NUM, "bogosize", "A meaningless metric for UTXO set size"},
-                        {RPCResult::Type::STR_HEX, "hash_serialized_2", "The serialized hash"},
+                        {RPCResult::Type::STR_HEX, "hash_serialized_2", "The serialized hash (only present if 'hash_serialized_2' hash_type is chosen)"},
                         {RPCResult::Type::NUM, "disk_size", "The estimated size of the chainstate on disk"},
                         {RPCResult::Type::STR_AMOUNT, "total_amount", "The total amount"},
                     }},
@@ -999,14 +1001,18 @@ static UniValue gettxoutsetinfo(const JSONRPCRequest& request)
     CCoinsStats stats;
     ::ChainstateActive().ForceFlushStateToDisk();
 
+    const CoinStatsHashType hash_type = ParseHashType(request.params[0], CoinStatsHashType::HASH_SERIALIZED);
+
     CCoinsView* coins_view = WITH_LOCK(cs_main, return &ChainstateActive().CoinsDB());
-    if (GetUTXOStats(coins_view, stats, RpcInterruptionPoint)) {
+    if (GetUTXOStats(coins_view, stats, hash_type, RpcInterruptionPoint)) {
         ret.pushKV("height", (int64_t)stats.nHeight);
         ret.pushKV("bestblock", stats.hashBlock.GetHex());
         ret.pushKV("transactions", (int64_t)stats.nTransactions);
         ret.pushKV("txouts", (int64_t)stats.nTransactionOutputs);
         ret.pushKV("bogosize", (int64_t)stats.nBogoSize);
-        ret.pushKV("hash_serialized_2", stats.hashSerialized.GetHex());
+        if (hash_type == CoinStatsHashType::HASH_SERIALIZED) {
+            ret.pushKV("hash_serialized_2", stats.hashSerialized.GetHex());
+        }
         ret.pushKV("disk_size", stats.nDiskSize);
         ret.pushKV("total_amount", ValueFromAmount(stats.nTotalAmount));
     } else {
@@ -2317,7 +2323,7 @@ UniValue dumptxoutset(const JSONRPCRequest& request)
 
         ::ChainstateActive().ForceFlushStateToDisk();
 
-        if (!GetUTXOStats(&::ChainstateActive().CoinsDB(), stats, RpcInterruptionPoint)) {
+        if (!GetUTXOStats(&::ChainstateActive().CoinsDB(), stats, CoinStatsHashType::NONE, RpcInterruptionPoint)) {
             throw JSONRPCError(RPC_INTERNAL_ERROR, "Unable to read UTXO set");
         }
 
@@ -2378,7 +2384,7 @@ static const CRPCCommand commands[] =
     { "blockchain",         "getmempoolinfo",         &getmempoolinfo,         {} },
     { "blockchain",         "getrawmempool",          &getrawmempool,          {"verbose"} },
     { "blockchain",         "gettxout",               &gettxout,               {"txid","n","include_mempool"} },
-    { "blockchain",         "gettxoutsetinfo",        &gettxoutsetinfo,        {} },
+    { "blockchain",         "gettxoutsetinfo",        &gettxoutsetinfo,        {"hash_type"} },
     { "blockchain",         "pruneblockchain",        &pruneblockchain,        {"height"} },
     { "blockchain",         "savemempool",            &savemempool,            {} },
     { "blockchain",         "verifychain",            &verifychain,            {"checklevel","nblocks"} },
diff --git a/src/rpc/util.cpp b/src/rpc/util.cpp
index 54ea352a72..ca73c699c9 100644
--- a/src/rpc/util.cpp
+++ b/src/rpc/util.cpp
@@ -113,6 +113,23 @@ std::vector<unsigned char> ParseHexO(const UniValue& o, std::string strKey)
     return ParseHexV(find_value(o, strKey), strKey);
 }
 
+CoinStatsHashType ParseHashType(const UniValue& param, const CoinStatsHashType default_type)
+{
+    if (param.isNull()) {
+        return default_type;
+    } else {
+        std::string hash_type_input = param.get_str();
+
+        if (hash_type_input == "hash_serialized_2") {
+            return CoinStatsHashType::HASH_SERIALIZED;
+        } else if (hash_type_input == "none") {
+            return CoinStatsHashType::NONE;
+        } else {
+            throw JSONRPCError(RPC_INVALID_PARAMETER, strprintf("%d is not a valid hash_type", hash_type_input));
+        }
+    }
+}
+
 std::string HelpExampleCli(const std::string& methodname, const std::string& args)
 {
     return "> bitcoin-cli " + methodname + " " + args + "\n";
diff --git a/src/rpc/util.h b/src/rpc/util.h
index 53dce2c397..96dd1ea74a 100644
--- a/src/rpc/util.h
+++ b/src/rpc/util.h
@@ -5,6 +5,7 @@
 #ifndef BITCOIN_RPC_UTIL_H
 #define BITCOIN_RPC_UTIL_H
 
+#include <node/coinstats.h>
 #include <node/transaction.h>
 #include <outputtype.h>
 #include <protocol.h>
@@ -77,6 +78,8 @@ extern uint256 ParseHashO(const UniValue& o, std::string strKey);
 extern std::vector<unsigned char> ParseHexV(const UniValue& v, std::string strName);
 extern std::vector<unsigned char> ParseHexO(const UniValue& o, std::string strKey);
 
+CoinStatsHashType ParseHashType(const UniValue& param, const CoinStatsHashType default_type);
+
 extern CAmount AmountFromValue(const UniValue& value);
 extern std::string HelpExampleCli(const std::string& methodname, const std::string& args);
 extern std::string HelpExampleRpc(const std::string& methodname, const std::string& args);