Refactor: split network transport deserializing from message container

4 files changed, 107 insertions, 48 deletions

diff --git a/src/net.cpp b/src/net.cpp
index 63b7833822..bd183ce52b 100644
--- a/src/net.cpp
+++ b/src/net.cpp
@@ -570,42 +570,42 @@ bool CNode::ReceiveMsgBytes(const char *pch, unsigned int nBytes, bool& complete
     nLastRecv = nTimeMicros / 1000000;
     nRecvBytes += nBytes;
     while (nBytes > 0) {
-
-        // get current incomplete message, or create a new one
-        if (vRecvMsg.empty() ||
-            vRecvMsg.back().complete())
-            vRecvMsg.push_back(CNetMessage(Params().MessageStart(), SER_NETWORK, INIT_PROTO_VERSION));
-
-        CNetMessage& msg = vRecvMsg.back();
-
         // absorb network data
         int handled;
-        if (!msg.in_data)
-            handled = msg.readHeader(pch, nBytes);
+        if (!m_deserializer->in_data)
+            handled = m_deserializer->readHeader(pch, nBytes);
         else
-            handled = msg.readData(pch, nBytes);
+            handled = m_deserializer->readData(pch, nBytes);
 
-        if (handled < 0)
+        if (handled < 0) {
+            m_deserializer->Reset();
             return false;
+        }
 
-        if (msg.in_data && msg.hdr.nMessageSize > MAX_PROTOCOL_MESSAGE_LENGTH) {
+        if (m_deserializer->in_data && m_deserializer->hdr.nMessageSize > MAX_PROTOCOL_MESSAGE_LENGTH) {
             LogPrint(BCLog::NET, "Oversized message from peer=%i, disconnecting\n", GetId());
+            m_deserializer->Reset();
             return false;
         }
 
         pch += handled;
         nBytes -= handled;
 
-        if (msg.complete()) {
+        if (m_deserializer->complete()) {
+            // decompose a transport agnostic CNetMessage from the deserializer
+            CNetMessage msg = m_deserializer->GetMessage(Params().MessageStart(), nTimeMicros);
+
             //store received bytes per message command
             //to prevent a memory DOS, only allow valid commands
-            mapMsgCmdSize::iterator i = mapRecvBytesPerMsgCmd.find(msg.hdr.pchCommand);
+            mapMsgCmdSize::iterator i = mapRecvBytesPerMsgCmd.find(m_deserializer->hdr.pchCommand);
             if (i == mapRecvBytesPerMsgCmd.end())
                 i = mapRecvBytesPerMsgCmd.find(NET_MESSAGE_COMMAND_OTHER);
             assert(i != mapRecvBytesPerMsgCmd.end());
-            i->second += msg.hdr.nMessageSize + CMessageHeader::HEADER_SIZE;
+            i->second += m_deserializer->hdr.nMessageSize + CMessageHeader::HEADER_SIZE;
+
+            // push the message to the process queue,
+            vRecvMsg.push_back(std::move(msg));
 
-            msg.nTime = nTimeMicros;
             complete = true;
         }
     }
@@ -639,8 +639,7 @@ int CNode::GetSendVersion() const
     return nSendVersion;
 }
 
-
-int CNetMessage::readHeader(const char *pch, unsigned int nBytes)
+int TransportDeserializer::readHeader(const char *pch, unsigned int nBytes)
 {
     // copy data to temporary parsing buffer
     unsigned int nRemaining = 24 - nHdrPos;
@@ -671,7 +670,7 @@ int CNetMessage::readHeader(const char *pch, unsigned int nBytes)
     return nCopy;
 }
 
-int CNetMessage::readData(const char *pch, unsigned int nBytes)
+int TransportDeserializer::readData(const char *pch, unsigned int nBytes)
 {
     unsigned int nRemaining = hdr.nMessageSize - nDataPos;
     unsigned int nCopy = std::min(nRemaining, nBytes);
@@ -688,7 +687,7 @@ int CNetMessage::readData(const char *pch, unsigned int nBytes)
     return nCopy;
 }
 
-const uint256& CNetMessage::GetMessageHash() const
+const uint256& TransportDeserializer::GetMessageHash() const
 {
     assert(complete());
     if (data_hash.IsNull())
@@ -696,6 +695,35 @@ const uint256& CNetMessage::GetMessageHash() const
     return data_hash;
 }
 
+CNetMessage TransportDeserializer::GetMessage(const CMessageHeader::MessageStartChars& message_start, int64_t time) {
+    // decompose a single CNetMessage from the TransportDeserializer
+    CNetMessage msg(std::move(vRecv));
+
+    // store state about valid header, netmagic and checksum
+    msg.m_valid_header = hdr.IsValid(message_start);
+    msg.m_valid_netmagic = (memcmp(hdr.pchMessageStart, message_start, CMessageHeader::MESSAGE_START_SIZE) == 0);
+    uint256 hash = GetMessageHash();
+
+    // store command string, payload size
+    msg.m_command = hdr.GetCommand();
+    msg.m_message_size = hdr.nMessageSize;
+
+    msg.m_valid_checksum = (memcmp(hash.begin(), hdr.pchChecksum, CMessageHeader::CHECKSUM_SIZE) == 0);
+    if (!msg.m_valid_checksum) {
+        LogPrint(BCLog::NET, "CHECKSUM ERROR (%s, %u bytes), expected %s was %s\n",
+                 SanitizeString(msg.m_command), msg.m_message_size,
+                 HexStr(hash.begin(), hash.begin()+CMessageHeader::CHECKSUM_SIZE),
+                 HexStr(hdr.pchChecksum, hdr.pchChecksum+CMessageHeader::CHECKSUM_SIZE));
+    }
+
+    // store receive time
+    msg.m_time = time;
+
+    // reset the network deserializer (prepare for the next message)
+    Reset();
+    return msg;
+}
+
 size_t CConnman::SocketSendData(CNode *pnode) const EXCLUSIVE_LOCKS_REQUIRED(pnode->cs_vSend)
 {
     auto it = pnode->vSendMsg.begin();
@@ -1347,9 +1375,9 @@ void CConnman::SocketHandler()
                     size_t nSizeAdded = 0;
                     auto it(pnode->vRecvMsg.begin());
                     for (; it != pnode->vRecvMsg.end(); ++it) {
-                        if (!it->complete())
-                            break;
-                        nSizeAdded += it->vRecv.size() + CMessageHeader::HEADER_SIZE;
+                        // vRecvMsg contains only completed CNetMessage
+                        // the single possible partially deserialized message are held by TransportDeserializer
+                        nSizeAdded += it->m_recv.size() + CMessageHeader::HEADER_SIZE;
                     }
                     {
                         LOCK(pnode->cs_vProcessMsg);
@@ -2678,6 +2706,8 @@ CNode::CNode(NodeId idIn, ServiceFlags nLocalServicesIn, int nMyStartingHeightIn
     } else {
         LogPrint(BCLog::NET, "Added connection peer=%d\n", id);
     }
+
+    m_deserializer = MakeUnique<TransportDeserializer>(TransportDeserializer(Params().MessageStart(), SER_NETWORK, INIT_PROTO_VERSION));
 }
 
 CNode::~CNode()
diff --git a/src/net.h b/src/net.h
index 44655abf80..a9ce33957d 100644
--- a/src/net.h
+++ b/src/net.h
@@ -609,8 +609,33 @@ public:
 
 
 
-
+/** Transport protocol agnostic message container.
+ * Ideally it should only contain receive time, payload,
+ * command and size.
+ */
 class CNetMessage {
+public:
+    CDataStream m_recv;                  // received message data
+    int64_t m_time = 0;                  // time (in microseconds) of message receipt.
+    bool m_valid_netmagic = false;
+    bool m_valid_header = false;
+    bool m_valid_checksum = false;
+    uint32_t m_message_size = 0;         // size of the payload
+    std::string m_command;
+
+    CNetMessage(const CDataStream& recv_in) : m_recv(std::move(recv_in)) {}
+
+    void SetVersion(int nVersionIn)
+    {
+        m_recv.SetVersion(nVersionIn);
+    }
+};
+
+/** The TransportDeserializer takes care of holding and deserializing the
+ * network receive buffer. It can deserialize the network buffer into a
+ * transport protocol agnostic CNetMessage (command & payload)
+ */
+class TransportDeserializer {
 private:
     mutable CHash256 hasher;
     mutable uint256 data_hash;
@@ -624,14 +649,19 @@ public:
     CDataStream vRecv;              // received message data
     unsigned int nDataPos;
 
-    int64_t nTime;                  // time (in microseconds) of message receipt.
+    TransportDeserializer(const CMessageHeader::MessageStartChars& pchMessageStartIn, int nTypeIn, int nVersionIn) : hdrbuf(nTypeIn, nVersionIn), hdr(pchMessageStartIn), vRecv(nTypeIn, nVersionIn) {
+        Reset();
+    }
 
-    CNetMessage(const CMessageHeader::MessageStartChars& pchMessageStartIn, int nTypeIn, int nVersionIn) : hdrbuf(nTypeIn, nVersionIn), hdr(pchMessageStartIn), vRecv(nTypeIn, nVersionIn) {
+    void Reset() {
+        vRecv.clear();
+        hdrbuf.clear();
         hdrbuf.resize(24);
         in_data = false;
         nHdrPos = 0;
         nDataPos = 0;
-        nTime = 0;
+        data_hash.SetNull();
+        hasher.Reset();
     }
 
     bool complete() const
@@ -651,14 +681,17 @@ public:
 
     int readHeader(const char *pch, unsigned int nBytes);
     int readData(const char *pch, unsigned int nBytes);
-};
 
+    CNetMessage GetMessage(const CMessageHeader::MessageStartChars& message_start, int64_t time);
+};
 
 /** Information about a peer */
 class CNode
 {
     friend class CConnman;
 public:
+    std::unique_ptr<TransportDeserializer> m_deserializer;
+
     // socket
     std::atomic<ServiceFlags> nServices{NODE_NONE};
     SOCKET hSocket GUARDED_BY(cs_hSocket);
diff --git a/src/net_processing.cpp b/src/net_processing.cpp
index b6839dcf21..c8ffbbbe9d 100644
--- a/src/net_processing.cpp
+++ b/src/net_processing.cpp
@@ -3260,41 +3260,37 @@ bool PeerLogicValidation::ProcessMessages(CNode* pfrom, std::atomic<bool>& inter
             return false;
         // Just take one message
         msgs.splice(msgs.begin(), pfrom->vProcessMsg, pfrom->vProcessMsg.begin());
-        pfrom->nProcessQueueSize -= msgs.front().vRecv.size() + CMessageHeader::HEADER_SIZE;
+        pfrom->nProcessQueueSize -= msgs.front().m_recv.size() + CMessageHeader::HEADER_SIZE;
         pfrom->fPauseRecv = pfrom->nProcessQueueSize > connman->GetReceiveFloodSize();
         fMoreWork = !pfrom->vProcessMsg.empty();
     }
     CNetMessage& msg(msgs.front());
 
     msg.SetVersion(pfrom->GetRecvVersion());
-    // Scan for message start
-    if (memcmp(msg.hdr.pchMessageStart, chainparams.MessageStart(), CMessageHeader::MESSAGE_START_SIZE) != 0) {
-        LogPrint(BCLog::NET, "PROCESSMESSAGE: INVALID MESSAGESTART %s peer=%d\n", SanitizeString(msg.hdr.GetCommand()), pfrom->GetId());
+    // Check network magic
+    if (!msg.m_valid_netmagic) {
+        LogPrint(BCLog::NET, "PROCESSMESSAGE: INVALID MESSAGESTART %s peer=%d\n", SanitizeString(msg.m_command), pfrom->GetId());
         pfrom->fDisconnect = true;
         return false;
     }
 
-    // Read header
-    CMessageHeader& hdr = msg.hdr;
-    if (!hdr.IsValid(chainparams.MessageStart()))
+    // Check header
+    if (!msg.m_valid_header)
     {
-        LogPrint(BCLog::NET, "PROCESSMESSAGE: ERRORS IN HEADER %s peer=%d\n", SanitizeString(hdr.GetCommand()), pfrom->GetId());
+        LogPrint(BCLog::NET, "PROCESSMESSAGE: ERRORS IN HEADER %s peer=%d\n", SanitizeString(msg.m_command), pfrom->GetId());
         return fMoreWork;
     }
-    std::string strCommand = hdr.GetCommand();
+    const std::string& strCommand = msg.m_command;
 
     // Message size
-    unsigned int nMessageSize = hdr.nMessageSize;
+    unsigned int nMessageSize = msg.m_message_size;
 
     // Checksum
-    CDataStream& vRecv = msg.vRecv;
-    const uint256& hash = msg.GetMessageHash();
-    if (memcmp(hash.begin(), hdr.pchChecksum, CMessageHeader::CHECKSUM_SIZE) != 0)
+    CDataStream& vRecv = msg.m_recv;
+    if (!msg.m_valid_checksum)
     {
-        LogPrint(BCLog::NET, "%s(%s, %u bytes): CHECKSUM ERROR expected %s was %s\n", __func__,
-           SanitizeString(strCommand), nMessageSize,
-           HexStr(hash.begin(), hash.begin()+CMessageHeader::CHECKSUM_SIZE),
-           HexStr(hdr.pchChecksum, hdr.pchChecksum+CMessageHeader::CHECKSUM_SIZE));
+        LogPrint(BCLog::NET, "%s(%s, %u bytes): CHECKSUM ERROR peer=%d\n", __func__,
+           SanitizeString(strCommand), nMessageSize, pfrom->GetId());
         return fMoreWork;
     }
 
@@ -3302,7 +3298,7 @@ bool PeerLogicValidation::ProcessMessages(CNode* pfrom, std::atomic<bool>& inter
     bool fRet = false;
     try
     {
-        fRet = ProcessMessage(pfrom, strCommand, vRecv, msg.nTime, chainparams, connman, interruptMsgProc);
+        fRet = ProcessMessage(pfrom, strCommand, vRecv, msg.m_time, chainparams, connman, interruptMsgProc);
         if (interruptMsgProc)
             return false;
         if (!pfrom->vRecvGetData.empty())
diff --git a/test/functional/p2p_invalid_messages.py b/test/functional/p2p_invalid_messages.py
index 58c72f89d8..8fcf5b878f 100755
--- a/test/functional/p2p_invalid_messages.py
+++ b/test/functional/p2p_invalid_messages.py
@@ -168,7 +168,7 @@ class InvalidMessagesTest(BitcoinTestFramework):
 
     def test_checksum(self):
         conn = self.nodes[0].add_p2p_connection(P2PDataStore())
-        with self.nodes[0].assert_debug_log(['ProcessMessages(badmsg, 2 bytes): CHECKSUM ERROR expected 78df0a04 was ffffffff']):
+        with self.nodes[0].assert_debug_log(['CHECKSUM ERROR (badmsg, 2 bytes), expected 78df0a04 was ffffffff']):
             msg = conn.build_message(msg_unrecognized(str_data="d"))
             cut_len = (
                 4 +  # magic