Add merkle.{h,cpp}, generic merkle root/branch algorithm

src/Makefile.am

@@ -100,6 +100,7 @@ BITCOIN_CORE_H = \
   compat/sanity.h \
   compressor.h \
   consensus/consensus.h \
+  consensus/merkle.h \
   consensus/params.h \
   consensus/validation.h \
   core_io.h \
@@ -268,6 +269,7 @@ libbitcoin_common_a_SOURCES = \
   chainparams.cpp \
   coins.cpp \
   compressor.cpp \
+  consensus/merkle.cpp \
   core_read.cpp \
   core_write.cpp \
   hash.cpp \

src/consensus/merkle.cpp

@@ -0,0 +1,152 @@
+#include "merkle.h"
+#include "hash.h"
+#include "utilstrencodings.h"
+
+/*     WARNING! If you're reading this because you're learning about crypto
+       and/or designing a new system that will use merkle trees, keep in mind
+       that the following merkle tree algorithm has a serious flaw related to
+       duplicate txids, resulting in a vulnerability (CVE-2012-2459).
+
+       The reason is that if the number of hashes in the list at a given time
+       is odd, the last one is duplicated before computing the next level (which
+       is unusual in Merkle trees). This results in certain sequences of
+       transactions leading to the same merkle root. For example, these two
+       trees:
+
+                    A               A
+                  /  \            /   \
+                B     C         B       C
+               / \    |        / \     / \
+              D   E   F       D   E   F   F
+             / \ / \ / \     / \ / \ / \ / \
+             1 2 3 4 5 6     1 2 3 4 5 6 5 6
+
+       for transaction lists [1,2,3,4,5,6] and [1,2,3,4,5,6,5,6] (where 5 and
+       6 are repeated) result in the same root hash A (because the hash of both
+       of (F) and (F,F) is C).
+
+       The vulnerability results from being able to send a block with such a
+       transaction list, with the same merkle root, and the same block hash as
+       the original without duplication, resulting in failed validation. If the
+       receiving node proceeds to mark that block as permanently invalid
+       however, it will fail to accept further unmodified (and thus potentially
+       valid) versions of the same block. We defend against this by detecting
+       the case where we would hash two identical hashes at the end of the list
+       together, and treating that identically to the block having an invalid
+       merkle root. Assuming no double-SHA256 collisions, this will detect all
+       known ways of changing the transactions without affecting the merkle
+       root.
+*/
+
+/* This implements a constant-space merkle root/path calculator, limited to 2^32 leaves. */
+static void MerkleComputation(const std::vector<uint256>& leaves, uint256* proot, bool* pmutated, uint32_t branchpos, std::vector<uint256>* pbranch) {
+    if (pbranch) pbranch->clear();
+    if (leaves.size() == 0) {
+        if (pmutated) *pmutated = false;
+        if (proot) *proot = uint256();
+        return;
+    }
+    bool mutated = false;
+    // count is the number of leaves processed so far.
+    uint32_t count = 0;
+    // inner is an array of eagerly computed subtree hashes, indexed by tree
+    // level (0 being the leaves).
+    // For example, when count is 25 (11001 in binary), inner[4] is the hash of
+    // the first 16 leaves, inner[3] of the next 8 leaves, and inner[0] equal to
+    // the last leaf. The other inner entries are undefined.
+    uint256 inner[32];
+    // Which position in inner is a hash that depends on the matching leaf.
+    int matchlevel = -1;
+    // First process all leaves into 'inner' values.
+    while (count < leaves.size()) {
+        uint256 h = leaves[count];
+        bool matchh = count == branchpos;
+        count++;
+        int level;
+        // For each of the lower bits in count that are 0, do 1 step. Each
+        // corresponds to an inner value that existed before processing the
+        // current leaf, and each needs a hash to combine it.
+        for (level = 0; !(count & (((uint32_t)1) << level)); level++) {
+            if (pbranch) {
+                if (matchh) {
+                    pbranch->push_back(inner[level]);
+                } else if (matchlevel == level) {
+                    pbranch->push_back(h);
+                    matchh = true;
+                }
+            }
+            mutated |= (inner[level] == h);
+            CHash256().Write(inner[level].begin(), 32).Write(h.begin(), 32).Finalize(h.begin());
+        }
+        // Store the resulting hash at inner position level.
+        inner[level] = h;
+        if (matchh) {
+            matchlevel = level;
+        }
+    }
+    // Do a final 'sweep' over the rightmost branch of the tree to process
+    // odd levels, and reduce everything to a single top value.
+    // Level is the level (counted from the bottom) up to which we've sweeped.
+    int level = 0;
+    // As long as bit number level in count is zero, skip it. It means there
+    // is nothing left at this level.
+    while (!(count & (((uint32_t)1) << level))) {
+        level++;
+    }
+    uint256 h = inner[level];
+    bool matchh = matchlevel == level;
+    while (count != (((uint32_t)1) << level)) {
+        // If we reach this point, h is an inner value that is not the top.
+        // We combine it with itself (Bitcoin's special rule for odd levels in
+        // the tree) to produce a higher level one.
+        if (pbranch && matchh) {
+            pbranch->push_back(h);
+        }
+        CHash256().Write(h.begin(), 32).Write(h.begin(), 32).Finalize(h.begin());
+        // Increment count to the value it would have if two entries at this
+        // level had existed.
+        count += (((uint32_t)1) << level);
+        level++;
+        // And propagate the result upwards accordingly.
+        while (!(count & (((uint32_t)1) << level))) {
+            if (pbranch) {
+                if (matchh) {
+                    pbranch->push_back(inner[level]);
+                } else if (matchlevel == level) {
+                    pbranch->push_back(h);
+                    matchh = true;
+                }
+            }
+            CHash256().Write(inner[level].begin(), 32).Write(h.begin(), 32).Finalize(h.begin());
+            level++;
+        }
+    }
+    // Return result.
+    if (pmutated) *pmutated = mutated;
+    if (proot) *proot = h;
+}
+
+uint256 ComputeMerkleRoot(const std::vector<uint256>& leaves, bool* mutated) {
+    uint256 hash;
+    MerkleComputation(leaves, &hash, mutated, -1, NULL);
+    return hash;
+}
+
+std::vector<uint256> ComputeMerkleBranch(const std::vector<uint256>& leaves, uint32_t position) {
+    std::vector<uint256> ret;
+    MerkleComputation(leaves, NULL, NULL, position, &ret);
+    return ret;
+}
+
+uint256 ComputeMerkleRootFromBranch(const uint256& leaf, const std::vector<uint256>& vMerkleBranch, uint32_t nIndex) {
+    uint256 hash = leaf;
+    for (std::vector<uint256>::const_iterator it = vMerkleBranch.begin(); it != vMerkleBranch.end(); ++it) {
+        if (nIndex & 1) {
+            hash = Hash(BEGIN(*it), END(*it), BEGIN(hash), END(hash));
+        } else {
+            hash = Hash(BEGIN(hash), END(hash), BEGIN(*it), END(*it));
+        }
+        nIndex >>= 1;
+    }
+    return hash;
+}

src/consensus/merkle.h

@@ -0,0 +1,17 @@
+// Copyright (c) 2015 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_MERKLE
+#define BITCOIN_MERKLE
+
+#include <stdint.h>
+#include <vector>
+
+#include "uint256.h"
+
+uint256 ComputeMerkleRoot(const std::vector<uint256>& leaves, bool* mutated = NULL);
+std::vector<uint256> ComputeMerkleBranch(const std::vector<uint256>& leaves, uint32_t position);
+uint256 ComputeMerkleRootFromBranch(const uint256& leaf, const std::vector<uint256>& branch, uint32_t position);
+
+#endif