From 0aa874a357865dd4768091f26dff238e66fb8d83 Mon Sep 17 00:00:00 2001
From: Pieter Wuille <pieter@wuille.net>
Date: Fri, 25 Oct 2024 14:11:50 -0400
Subject: [PATCH] clusterlin: Add FixLinearization function + fuzz test

This function takes an existing ordering for transactions in a DepGraph, and
makes it a valid linearization for it (i.e., topological). Any topological
prefix of the input remains untouched.
---
 src/cluster_linearize.h             | 32 +++++++++++++++
 src/test/fuzz/cluster_linearize.cpp | 62 +++++++++++++++++++++++++++++
 2 files changed, 94 insertions(+)

diff --git a/src/cluster_linearize.h b/src/cluster_linearize.h
index 7c7401706f6..32cedf9f840 100644
--- a/src/cluster_linearize.h
+++ b/src/cluster_linearize.h
@@ -1336,6 +1336,38 @@ std::vector<ClusterIndex> MergeLinearizations(const DepGraph<SetType>& depgraph,
     return ret;
 }
 
+/** Make linearization topological, retaining its ordering where possible. */
+template<typename SetType>
+void FixLinearization(const DepGraph<SetType>& depgraph, std::span<ClusterIndex> linearization) noexcept
+{
+    // This algorithm can be summarized as moving every element in the linearization backwards
+    // until it is placed after all its ancestors.
+    SetType done;
+    const auto len = linearization.size();
+    // Iterate over the elements of linearization from back to front (i is distance from back).
+    for (ClusterIndex i = 0; i < len; ++i) {
+        /** The element at that position. */
+        ClusterIndex elem = linearization[len - 1 - i];
+        /** j represents how far from the back of the linearization elem should be placed. */
+        ClusterIndex j = i;
+        // Figure out which elements need to be moved before elem.
+        SetType place_before = done & depgraph.Ancestors(elem);
+        // Find which position to place elem in (updating j), continuously moving the elements
+        // in between forward.
+        while (place_before.Any()) {
+            // j cannot be 0 here; if it was, then there was necessarily nothing earlier which
+            // elem needs to be place before anymore, and place_before would be empty.
+            Assume(j > 0);
+            auto to_swap = linearization[len - 1 - (j - 1)];
+            place_before.Reset(to_swap);
+            linearization[len - 1 - (j--)] = to_swap;
+        }
+        // Put elem in its final position and mark it as done.
+        linearization[len - 1 - j] = elem;
+        done.Set(elem);
+    }
+}
+
 } // namespace cluster_linearize
 
 #endif // BITCOIN_CLUSTER_LINEARIZE_H
diff --git a/src/test/fuzz/cluster_linearize.cpp b/src/test/fuzz/cluster_linearize.cpp
index 5b3770636ab..de066237b2a 100644
--- a/src/test/fuzz/cluster_linearize.cpp
+++ b/src/test/fuzz/cluster_linearize.cpp
@@ -1118,3 +1118,65 @@ FUZZ_TARGET(clusterlin_merge)
     auto cmp2 = CompareChunks(chunking_merged, chunking2);
     assert(cmp2 >= 0);
 }
+
+FUZZ_TARGET(clusterlin_fix_linearization)
+{
+    // Verify expected properties of FixLinearization() on arbitrary linearizations.
+
+    // Retrieve a depgraph from the fuzz input.
+    SpanReader reader(buffer);
+    DepGraph<TestBitSet> depgraph;
+    try {
+        reader >> Using<DepGraphFormatter>(depgraph);
+    } catch (const std::ios_base::failure&) {}
+
+    // Construct an arbitrary linearization (not necessarily topological for depgraph).
+    std::vector<ClusterIndex> linearization;
+    /** Which transactions of depgraph are yet to be included in linearization. */
+    TestBitSet todo = depgraph.Positions();
+    while (todo.Any()) {
+        // Read a number from the fuzz input in range [0, todo.Count()).
+        uint64_t val{0};
+        try {
+            reader >> VARINT(val);
+        } catch (const std::ios_base::failure&) {}
+        val %= todo.Count();
+        // Find the val'th element in todo, remove it from todo, and append it to linearization.
+        for (auto idx : todo) {
+            if (val == 0) {
+                linearization.push_back(idx);
+                todo.Reset(idx);
+                break;
+            }
+            --val;
+        }
+    }
+    assert(linearization.size() == depgraph.TxCount());
+
+    // Determine what prefix of linearization is topological, i.e., the position of the first entry
+    // in linearization which corresponds to a transaction that is not preceded by all its
+    // ancestors.
+    size_t topo_prefix = 0;
+    todo = depgraph.Positions();
+    while (topo_prefix < linearization.size()) {
+        ClusterIndex idx = linearization[topo_prefix];
+        todo.Reset(idx);
+        if (todo.Overlaps(depgraph.Ancestors(idx))) break;
+        ++topo_prefix;
+    }
+
+    // Then make a fixed copy of linearization.
+    auto linearization_fixed = linearization;
+    FixLinearization(depgraph, linearization_fixed);
+    // Sanity check it (which includes testing whether it is topological).
+    SanityCheck(depgraph, linearization_fixed);
+
+    // FixLinearization does not modify the topological prefix of linearization.
+    assert(std::equal(linearization.begin(), linearization.begin() + topo_prefix,
+                      linearization_fixed.begin()));
+    // This also means that if linearization was entirely topological, FixLinearization cannot have
+    // modified it. This is implied by the assertion above already, but repeat it explicitly.
+    if (topo_prefix == linearization.size()) {
+        assert(linearization == linearization_fixed);
+    }
+}