[clang] Fix quadratic slowdown in AST matcher parent map generation (PR #87824)

[via cfe-commits]

https://github.com/higher-performance updated https://github.com/llvm/llvm-project/pull/87824

>From 78f18445804fdb1cdf7810f56d3ae3c6e55f8da7 Mon Sep 17 00:00:00 2001
From: higher-performance
 <113926381+higher-performance at users.noreply.github.com>
Date: Fri, 5 Apr 2024 15:36:05 -0400
Subject: [PATCH] Fix quadratic slowdown in AST matcher parent map generation

Avoids the need to linearly re-scan all seen parent nodes to check for duplicates, which previously caused a slowdown for ancestry checks in Clang AST matchers.

Fixes https://github.com/llvm/llvm-project/issues/86881.
---
 clang/docs/ReleaseNotes.rst        |  3 +++
 clang/lib/AST/ParentMapContext.cpp | 25 ++++++++++++++++++++++---
 2 files changed, 25 insertions(+), 3 deletions(-)

diff --git a/clang/docs/ReleaseNotes.rst b/clang/docs/ReleaseNotes.rst
index 28e8ddb3c41c3e..cd9e0b54d55fde 100644
--- a/clang/docs/ReleaseNotes.rst
+++ b/clang/docs/ReleaseNotes.rst
@@ -622,6 +622,9 @@ Fixed Point Support in Clang
 AST Matchers
 ------------
 
+- Fixes a long-standing performance issue in parent map generation for
+  ancestry-based matchers such as ``hasParent`` and ``hasAncestor``, making
+  them significantly faster.
 - ``isInStdNamespace`` now supports Decl declared with ``extern "C++"``.
 - Add ``isExplicitObjectMemberFunction``.
 - Fixed ``forEachArgumentWithParam`` and ``forEachArgumentWithParamType`` to
diff --git a/clang/lib/AST/ParentMapContext.cpp b/clang/lib/AST/ParentMapContext.cpp
index 21cfd5b1de6e9d..9723c0cfa83bbe 100644
--- a/clang/lib/AST/ParentMapContext.cpp
+++ b/clang/lib/AST/ParentMapContext.cpp
@@ -61,7 +61,26 @@ class ParentMapContext::ParentMap {
   template <typename, typename...> friend struct ::MatchParents;
 
   /// Contains parents of a node.
-  using ParentVector = llvm::SmallVector<DynTypedNode, 2>;
+  class ParentVector {
+  public:
+    ParentVector() = default;
+    explicit ParentVector(size_t N, const DynTypedNode &Value) {
+      Items.reserve(N);
+      for (; N > 0; --N)
+        push_back(Value);
+    }
+    bool contains(const DynTypedNode &Value) {
+      return Seen.contains(Value);
+    }
+    void push_back(const DynTypedNode &Value) {
+      if (!Value.getMemoizationData() || Seen.insert(Value).second)
+        Items.push_back(Value);
+    }
+    llvm::ArrayRef<DynTypedNode> view() const { return Items; }
+  private:
+    llvm::SmallVector<DynTypedNode, 2> Items;
+    llvm::SmallDenseSet<DynTypedNode, 2> Seen;
+  };
 
   /// Maps from a node to its parents. This is used for nodes that have
   /// pointer identity only, which are more common and we can save space by
@@ -99,7 +118,7 @@ class ParentMapContext::ParentMap {
       return llvm::ArrayRef<DynTypedNode>();
     }
     if (const auto *V = I->second.template dyn_cast<ParentVector *>()) {
-      return llvm::ArrayRef(*V);
+      return V->view();
     }
     return getSingleDynTypedNodeFromParentMap(I->second);
   }
@@ -252,7 +271,7 @@ class ParentMapContext::ParentMap {
       const auto *S = It->second.dyn_cast<const Stmt *>();
       if (!S) {
         if (auto *Vec = It->second.dyn_cast<ParentVector *>())
-          return llvm::ArrayRef(*Vec);
+          return Vec->view();
         return getSingleDynTypedNodeFromParentMap(It->second);
       }
       const auto *P = dyn_cast<Expr>(S);