addrman.h

Go to the documentation of this file.

// Copyright (c) 2012 Pieter Wuille
// Copyright (c) 2012-2020 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_ADDRMAN_H
#define BITCOIN_ADDRMAN_H

#include <clientversion.h>
#include <config/bitcoin-config.h>
#include <fs.h>
#include <hash.h>
#include <netaddress.h>
#include <protocol.h>
#include <random.h>
#include <streams.h>
#include <sync.h>
#include <timedata.h>
#include <tinyformat.h>
#include <util/system.h>

#include <iostream>
#include <optional>
#include <set>
#include <stdint.h>
#include <unordered_map>
#include <vector>

class CAddrInfo : public CAddress
{
public:
    int64_t nLastTry{0};

    int64_t nLastCountAttempt{0};

private:
    CNetAddr source;

    int64_t nLastSuccess{0};

    int nAttempts{0};

    int nRefCount{0};

    bool fInTried{false};

    int nRandomPos{-1};

    friend class CAddrMan;

public:

    SERIALIZE_METHODS(CAddrInfo, obj)
    {
        READWRITEAS(CAddress, obj);
        READWRITE(obj.source, obj.nLastSuccess, obj.nAttempts);
    }

    CAddrInfo(const CAddress &addrIn, const CNetAddr &addrSource) : CAddress(addrIn), source(addrSource)
    {
    }

    CAddrInfo() : CAddress(), source()
    {
    }

    int GetTriedBucket(const uint256 &nKey, const std::vector<bool> &asmap) const;

    int GetNewBucket(const uint256 &nKey, const CNetAddr& src, const std::vector<bool> &asmap) const;

    int GetNewBucket(const uint256 &nKey, const std::vector<bool> &asmap) const
    {
        return GetNewBucket(nKey, source, asmap);
    }

    int GetBucketPosition(const uint256 &nKey, bool fNew, int nBucket) const;

    bool IsTerrible(int64_t nNow = GetAdjustedTime()) const;

    double GetChance(int64_t nNow = GetAdjustedTime()) const;
};

#define ADDRMAN_TRIED_BUCKET_COUNT_LOG2 8

#define ADDRMAN_NEW_BUCKET_COUNT_LOG2 10

#define ADDRMAN_BUCKET_SIZE_LOG2 6

#define ADDRMAN_TRIED_BUCKETS_PER_GROUP 8

#define ADDRMAN_NEW_BUCKETS_PER_SOURCE_GROUP 64

#define ADDRMAN_NEW_BUCKETS_PER_ADDRESS 8

#define ADDRMAN_HORIZON_DAYS 30

#define ADDRMAN_RETRIES 3

#define ADDRMAN_MAX_FAILURES 10

#define ADDRMAN_MIN_FAIL_DAYS 7

#define ADDRMAN_REPLACEMENT_HOURS 4

#define ADDRMAN_TRIED_BUCKET_COUNT (1 << ADDRMAN_TRIED_BUCKET_COUNT_LOG2)
#define ADDRMAN_NEW_BUCKET_COUNT (1 << ADDRMAN_NEW_BUCKET_COUNT_LOG2)
#define ADDRMAN_BUCKET_SIZE (1 << ADDRMAN_BUCKET_SIZE_LOG2)

#define ADDRMAN_SET_TRIED_COLLISION_SIZE 10

static const int64_t ADDRMAN_TEST_WINDOW = 40*60; // 40 minutes

class CAddrMan
{
public:
    // Compressed IP->ASN mapping, loaded from a file when a node starts.
    // Should be always empty if no file was provided.
    // This mapping is then used for bucketing nodes in Addrman.
    //
    // If asmap is provided, nodes will be bucketed by
    // AS they belong to, in order to make impossible for a node
    // to connect to several nodes hosted in a single AS.
    // This is done in response to Erebus attack, but also to generally
    // diversify the connections every node creates,
    // especially useful when a large fraction of nodes
    // operate under a couple of cloud providers.
    //
    // If a new asmap was provided, the existing records
    // would be re-bucketed accordingly.
    std::vector<bool> m_asmap;

    // Read asmap from provided binary file
    static std::vector<bool> DecodeAsmap(fs::path path);

    template <typename Stream>
    void Serialize(Stream& s_) const
        EXCLUSIVE_LOCKS_REQUIRED(!cs)
    {
        LOCK(cs);

        // Always serialize in the latest version (FILE_FORMAT).

        OverrideStream<Stream> s(&s_, s_.GetType(), s_.GetVersion() | ADDRV2_FORMAT);

        s << static_cast<uint8_t>(FILE_FORMAT);

        // Increment `lowest_compatible` iff a newly introduced format is incompatible with
        // the previous one.
        static constexpr uint8_t lowest_compatible = Format::V3_BIP155;
        s << static_cast<uint8_t>(INCOMPATIBILITY_BASE + lowest_compatible);

        s << nKey;
        s << nNew;
        s << nTried;

        int nUBuckets = ADDRMAN_NEW_BUCKET_COUNT ^ (1 << 30);
        s << nUBuckets;
        std::unordered_map<int, int> mapUnkIds;
        int nIds = 0;
        for (const auto& entry : mapInfo) {
            mapUnkIds[entry.first] = nIds;
            const CAddrInfo &info = entry.second;
            if (info.nRefCount) {
                assert(nIds != nNew); // this means nNew was wrong, oh ow
                s << info;
                nIds++;
            }
        }
        nIds = 0;
        for (const auto& entry : mapInfo) {
            const CAddrInfo &info = entry.second;
            if (info.fInTried) {
                assert(nIds != nTried); // this means nTried was wrong, oh ow
                s << info;
                nIds++;
            }
        }
        for (int bucket = 0; bucket < ADDRMAN_NEW_BUCKET_COUNT; bucket++) {
            int nSize = 0;
            for (int i = 0; i < ADDRMAN_BUCKET_SIZE; i++) {
                if (vvNew[bucket][i] != -1)
                    nSize++;
            }
            s << nSize;
            for (int i = 0; i < ADDRMAN_BUCKET_SIZE; i++) {
                if (vvNew[bucket][i] != -1) {
                    int nIndex = mapUnkIds[vvNew[bucket][i]];
                    s << nIndex;
                }
            }
        }
        // Store asmap checksum after bucket entries so that it
        // can be ignored by older clients for backward compatibility.
        uint256 asmap_checksum;
        if (m_asmap.size() != 0) {
            asmap_checksum = SerializeHash(m_asmap);
        }
        s << asmap_checksum;
    }

    template <typename Stream>
    void Unserialize(Stream& s_)
        EXCLUSIVE_LOCKS_REQUIRED(!cs)
    {
        LOCK(cs);

        assert(vRandom.empty());

        Format format;
        s_ >> Using<CustomUintFormatter<1>>(format);

        int stream_version = s_.GetVersion();
        if (format >= Format::V3_BIP155) {
            // Add ADDRV2_FORMAT to the version so that the CNetAddr and CAddress
            // unserialize methods know that an address in addrv2 format is coming.
            stream_version |= ADDRV2_FORMAT;
        }

        OverrideStream<Stream> s(&s_, s_.GetType(), stream_version);

        uint8_t compat;
        s >> compat;
        const uint8_t lowest_compatible = compat - INCOMPATIBILITY_BASE;
        if (lowest_compatible > FILE_FORMAT) {
            throw std::ios_base::failure(strprintf(
                "Unsupported format of addrman database: %u. It is compatible with formats >=%u, "
                "but the maximum supported by this version of %s is %u.",
                format, lowest_compatible, PACKAGE_NAME, static_cast<uint8_t>(FILE_FORMAT)));
        }

        s >> nKey;
        s >> nNew;
        s >> nTried;
        int nUBuckets = 0;
        s >> nUBuckets;
        if (format >= Format::V1_DETERMINISTIC) {
            nUBuckets ^= (1 << 30);
        }

        if (nNew > ADDRMAN_NEW_BUCKET_COUNT * ADDRMAN_BUCKET_SIZE || nNew < 0) {
            throw std::ios_base::failure(
                strprintf("Corrupt CAddrMan serialization: nNew=%d, should be in [0, %u]",
                          nNew,
                          ADDRMAN_NEW_BUCKET_COUNT * ADDRMAN_BUCKET_SIZE));
        }

        if (nTried > ADDRMAN_TRIED_BUCKET_COUNT * ADDRMAN_BUCKET_SIZE || nTried < 0) {
            throw std::ios_base::failure(
                strprintf("Corrupt CAddrMan serialization: nTried=%d, should be in [0, %u]",
                          nTried,
                          ADDRMAN_TRIED_BUCKET_COUNT * ADDRMAN_BUCKET_SIZE));
        }

        // Deserialize entries from the new table.
        for (int n = 0; n < nNew; n++) {
            CAddrInfo &info = mapInfo[n];
            s >> info;
            mapAddr[info] = n;
            info.nRandomPos = vRandom.size();
            vRandom.push_back(n);
        }
        nIdCount = nNew;

        // Deserialize entries from the tried table.
        int nLost = 0;
        for (int n = 0; n < nTried; n++) {
            CAddrInfo info;
            s >> info;
            int nKBucket = info.GetTriedBucket(nKey, m_asmap);
            int nKBucketPos = info.GetBucketPosition(nKey, false, nKBucket);
            if (vvTried[nKBucket][nKBucketPos] == -1) {
                info.nRandomPos = vRandom.size();
                info.fInTried = true;
                vRandom.push_back(nIdCount);
                mapInfo[nIdCount] = info;
                mapAddr[info] = nIdCount;
                vvTried[nKBucket][nKBucketPos] = nIdCount;
                nIdCount++;
            } else {
                nLost++;
            }
        }
        nTried -= nLost;

        // Store positions in the new table buckets to apply later (if possible).
        // An entry may appear in up to ADDRMAN_NEW_BUCKETS_PER_ADDRESS buckets,
        // so we store all bucket-entry_index pairs to iterate through later.
        std::vector<std::pair<int, int>> bucket_entries;

        for (int bucket = 0; bucket < nUBuckets; ++bucket) {
            int num_entries{0};
            s >> num_entries;
            for (int n = 0; n < num_entries; ++n) {
                int entry_index{0};
                s >> entry_index;
                if (entry_index >= 0 && entry_index < nNew) {
                    bucket_entries.emplace_back(bucket, entry_index);
                }
            }
        }

        // If the bucket count and asmap checksum haven't changed, then attempt
        // to restore the entries to the buckets/positions they were in before
        // serialization.
        uint256 supplied_asmap_checksum;
        if (m_asmap.size() != 0) {
            supplied_asmap_checksum = SerializeHash(m_asmap);
        }
        uint256 serialized_asmap_checksum;
        if (format >= Format::V2_ASMAP) {
            s >> serialized_asmap_checksum;
        }
        const bool restore_bucketing{nUBuckets == ADDRMAN_NEW_BUCKET_COUNT &&
                                     serialized_asmap_checksum == supplied_asmap_checksum};

        if (!restore_bucketing) {
            LogPrint(BCLog::ADDRMAN, "Bucketing method was updated, re-bucketing addrman entries from disk\n");
        }

        for (auto bucket_entry : bucket_entries) {
            int bucket{bucket_entry.first};
            const int entry_index{bucket_entry.second};
            CAddrInfo& info = mapInfo[entry_index];

            // The entry shouldn't appear in more than
            // ADDRMAN_NEW_BUCKETS_PER_ADDRESS. If it has already, just skip
            // this bucket_entry.
            if (info.nRefCount >= ADDRMAN_NEW_BUCKETS_PER_ADDRESS) continue;

            int bucket_position = info.GetBucketPosition(nKey, true, bucket);
            if (restore_bucketing && vvNew[bucket][bucket_position] == -1) {
                // Bucketing has not changed, using existing bucket positions for the new table
                vvNew[bucket][bucket_position] = entry_index;
                ++info.nRefCount;
            } else {
                // In case the new table data cannot be used (bucket count wrong or new asmap),
                // try to give them a reference based on their primary source address.
                bucket = info.GetNewBucket(nKey, m_asmap);
                bucket_position = info.GetBucketPosition(nKey, true, bucket);
                if (vvNew[bucket][bucket_position] == -1) {
                    vvNew[bucket][bucket_position] = entry_index;
                    ++info.nRefCount;
                }
            }
        }

        // Prune new entries with refcount 0 (as a result of collisions).
        int nLostUnk = 0;
        for (auto it = mapInfo.cbegin(); it != mapInfo.cend(); ) {
            if (it->second.fInTried == false && it->second.nRefCount == 0) {
                const auto itCopy = it++;
                Delete(itCopy->first);
                ++nLostUnk;
            } else {
                ++it;
            }
        }
        if (nLost + nLostUnk > 0) {
            LogPrint(BCLog::ADDRMAN, "addrman lost %i new and %i tried addresses due to collisions\n", nLostUnk, nLost);
        }

        RemoveInvalid();

        Check();
    }

    void Clear()
        EXCLUSIVE_LOCKS_REQUIRED(!cs)
    {
        LOCK(cs);
        std::vector<int>().swap(vRandom);
        nKey = insecure_rand.rand256();
        for (size_t bucket = 0; bucket < ADDRMAN_NEW_BUCKET_COUNT; bucket++) {
            for (size_t entry = 0; entry < ADDRMAN_BUCKET_SIZE; entry++) {
                vvNew[bucket][entry] = -1;
            }
        }
        for (size_t bucket = 0; bucket < ADDRMAN_TRIED_BUCKET_COUNT; bucket++) {
            for (size_t entry = 0; entry < ADDRMAN_BUCKET_SIZE; entry++) {
                vvTried[bucket][entry] = -1;
            }
        }

        nIdCount = 0;
        nTried = 0;
        nNew = 0;
        nLastGood = 1; //Initially at 1 so that "never" is strictly worse.
        mapInfo.clear();
        mapAddr.clear();
    }

    CAddrMan()
    {
        Clear();
    }

    ~CAddrMan()
    {
        nKey.SetNull();
    }

    size_t size() const
        EXCLUSIVE_LOCKS_REQUIRED(!cs)
    {
        LOCK(cs); // TODO: Cache this in an atomic to avoid this overhead
        return vRandom.size();
    }

    bool Add(const CAddress &addr, const CNetAddr& source, int64_t nTimePenalty = 0)
        EXCLUSIVE_LOCKS_REQUIRED(!cs)
    {
        LOCK(cs);
        bool fRet = false;
        Check();
        fRet |= Add_(addr, source, nTimePenalty);
        Check();
        if (fRet) {
            LogPrint(BCLog::ADDRMAN, "Added %s from %s: %i tried, %i new\n", addr.ToStringIPPort(), source.ToString(), nTried, nNew);
        }
        return fRet;
    }

    bool Add(const std::vector<CAddress> &vAddr, const CNetAddr& source, int64_t nTimePenalty = 0)
        EXCLUSIVE_LOCKS_REQUIRED(!cs)
    {
        LOCK(cs);
        int nAdd = 0;
        Check();
        for (std::vector<CAddress>::const_iterator it = vAddr.begin(); it != vAddr.end(); it++)
            nAdd += Add_(*it, source, nTimePenalty) ? 1 : 0;
        Check();
        if (nAdd) {
            LogPrint(BCLog::ADDRMAN, "Added %i addresses from %s: %i tried, %i new\n", nAdd, source.ToString(), nTried, nNew);
        }
        return nAdd > 0;
    }

    void Good(const CService &addr, bool test_before_evict = true, int64_t nTime = GetAdjustedTime())
        EXCLUSIVE_LOCKS_REQUIRED(!cs)
    {
        LOCK(cs);
        Check();
        Good_(addr, test_before_evict, nTime);
        Check();
    }

    void Attempt(const CService &addr, bool fCountFailure, int64_t nTime = GetAdjustedTime())
        EXCLUSIVE_LOCKS_REQUIRED(!cs)
    {
        LOCK(cs);
        Check();
        Attempt_(addr, fCountFailure, nTime);
        Check();
    }

    void ResolveCollisions()
        EXCLUSIVE_LOCKS_REQUIRED(!cs)
    {
        LOCK(cs);
        Check();
        ResolveCollisions_();
        Check();
    }

    CAddrInfo SelectTriedCollision()
        EXCLUSIVE_LOCKS_REQUIRED(!cs)
    {
        LOCK(cs);
        Check();
        const CAddrInfo ret = SelectTriedCollision_();
        Check();
        return ret;
    }

    CAddrInfo Select(bool newOnly = false)
        EXCLUSIVE_LOCKS_REQUIRED(!cs)
    {
        LOCK(cs);
        Check();
        const CAddrInfo addrRet = Select_(newOnly);
        Check();
        return addrRet;
    }

    std::vector<CAddress> GetAddr(size_t max_addresses, size_t max_pct, std::optional<Network> network)
        EXCLUSIVE_LOCKS_REQUIRED(!cs)
    {
        LOCK(cs);
        Check();
        std::vector<CAddress> vAddr;
        GetAddr_(vAddr, max_addresses, max_pct, network);
        Check();
        return vAddr;
    }

    void Connected(const CService &addr, int64_t nTime = GetAdjustedTime())
        EXCLUSIVE_LOCKS_REQUIRED(!cs)
    {
        LOCK(cs);
        Check();
        Connected_(addr, nTime);
        Check();
    }

    void SetServices(const CService &addr, ServiceFlags nServices)
        EXCLUSIVE_LOCKS_REQUIRED(!cs)
    {
        LOCK(cs);
        Check();
        SetServices_(addr, nServices);
        Check();
    }

protected:
    uint256 nKey;

    FastRandomContext insecure_rand;

private:
    mutable Mutex cs;

    enum Format : uint8_t {
        V0_HISTORICAL = 0,    
        V1_DETERMINISTIC = 1, 
        V2_ASMAP = 2,         
        V3_BIP155 = 3,        
    };

    static constexpr Format FILE_FORMAT = Format::V3_BIP155;

    static constexpr uint8_t INCOMPATIBILITY_BASE = 32;

    int nIdCount GUARDED_BY(cs);

    std::unordered_map<int, CAddrInfo> mapInfo GUARDED_BY(cs);

    std::unordered_map<CNetAddr, int, CNetAddrHash> mapAddr GUARDED_BY(cs);

    std::vector<int> vRandom GUARDED_BY(cs);

    // number of "tried" entries
    int nTried GUARDED_BY(cs);

    int vvTried[ADDRMAN_TRIED_BUCKET_COUNT][ADDRMAN_BUCKET_SIZE] GUARDED_BY(cs);

    int nNew GUARDED_BY(cs);

    int vvNew[ADDRMAN_NEW_BUCKET_COUNT][ADDRMAN_BUCKET_SIZE] GUARDED_BY(cs);

    int64_t nLastGood GUARDED_BY(cs);

    std::set<int> m_tried_collisions;

    CAddrInfo* Find(const CNetAddr& addr, int *pnId = nullptr) EXCLUSIVE_LOCKS_REQUIRED(cs);

    CAddrInfo* Create(const CAddress &addr, const CNetAddr &addrSource, int *pnId = nullptr) EXCLUSIVE_LOCKS_REQUIRED(cs);

    void SwapRandom(unsigned int nRandomPos1, unsigned int nRandomPos2) EXCLUSIVE_LOCKS_REQUIRED(cs);

    void MakeTried(CAddrInfo& info, int nId) EXCLUSIVE_LOCKS_REQUIRED(cs);

    void Delete(int nId) EXCLUSIVE_LOCKS_REQUIRED(cs);

    void ClearNew(int nUBucket, int nUBucketPos) EXCLUSIVE_LOCKS_REQUIRED(cs);

    void Good_(const CService &addr, bool test_before_evict, int64_t time) EXCLUSIVE_LOCKS_REQUIRED(cs);

    bool Add_(const CAddress &addr, const CNetAddr& source, int64_t nTimePenalty) EXCLUSIVE_LOCKS_REQUIRED(cs);

    void Attempt_(const CService &addr, bool fCountFailure, int64_t nTime) EXCLUSIVE_LOCKS_REQUIRED(cs);

    CAddrInfo Select_(bool newOnly) EXCLUSIVE_LOCKS_REQUIRED(cs);

    void ResolveCollisions_() EXCLUSIVE_LOCKS_REQUIRED(cs);

    CAddrInfo SelectTriedCollision_() EXCLUSIVE_LOCKS_REQUIRED(cs);

    void Check()
        EXCLUSIVE_LOCKS_REQUIRED(cs)
    {
#ifdef DEBUG_ADDRMAN
        AssertLockHeld(cs);
        const int err = Check_();
        if (err) {
            LogPrintf("ADDRMAN CONSISTENCY CHECK FAILED!!! err=%i\n", err);
        }
#endif
    }

#ifdef DEBUG_ADDRMAN
    int Check_() EXCLUSIVE_LOCKS_REQUIRED(cs);
#endif

    void GetAddr_(std::vector<CAddress>& vAddr, size_t max_addresses, size_t max_pct, std::optional<Network> network) EXCLUSIVE_LOCKS_REQUIRED(cs);

    void Connected_(const CService& addr, int64_t nTime) EXCLUSIVE_LOCKS_REQUIRED(cs);

    void SetServices_(const CService &addr, ServiceFlags nServices) EXCLUSIVE_LOCKS_REQUIRED(cs);

    void RemoveInvalid() EXCLUSIVE_LOCKS_REQUIRED(cs);

    friend class CAddrManTest;
};

#endif // BITCOIN_ADDRMAN_H