Merge branch 'main' into bi-prefetchw

Author: rnk

.github/workflows/libcxx-build-and-test.yaml

@@ -49,7 +49,8 @@ env:
 jobs:
   stage1:
     if: github.repository_owner == 'llvm'
-    runs-on: libcxx-runners-8-set
+    runs-on: libcxx-runners-set
+    container: ghcr.io/libcxx/actions-builder:testing-2024-09-21
     continue-on-error: false
     strategy:
       fail-fast: false
@@ -79,12 +80,14 @@ jobs:
           path: |
             **/test-results.xml
             **/*.abilist
+            **/CMakeConfigureLog.yaml
             **/CMakeError.log
             **/CMakeOutput.log
             **/crash_diagnostics/*
   stage2:
     if: github.repository_owner == 'llvm'
-    runs-on: libcxx-runners-8-set
+    runs-on: libcxx-runners-set
+    container: ghcr.io/libcxx/actions-builder:testing-2024-09-21
     needs: [ stage1 ]
     continue-on-error: false
     strategy:
@@ -123,6 +126,7 @@ jobs:
           path: |
             **/test-results.xml
             **/*.abilist
+            **/CMakeConfigureLog.yaml
             **/CMakeError.log
             **/CMakeOutput.log
             **/crash_diagnostics/*
@@ -160,20 +164,21 @@ jobs:
           'benchmarks',
           'bootstrapping-build'
         ]
-        machine: [ 'libcxx-runners-8-set' ]
+        machine: [ 'libcxx-runners-set' ]
         include:
         - config: 'generic-cxx26'
-          machine: libcxx-runners-8-set
+          machine: libcxx-runners-set
         - config: 'generic-asan'
-          machine: libcxx-runners-8-set
+          machine: libcxx-runners-set
         - config: 'generic-tsan'
-          machine: libcxx-runners-8-set
+          machine: libcxx-runners-set
         - config: 'generic-ubsan'
-          machine: libcxx-runners-8-set
+          machine: libcxx-runners-set
         # Use a larger machine for MSAN to avoid timeout and memory allocation issues.
         - config: 'generic-msan'
-          machine: libcxx-runners-8-set
+          machine: libcxx-runners-set
     runs-on: ${{ matrix.machine }}
+    container: ghcr.io/libcxx/actions-builder:testing-2024-09-21
     steps:
       - uses: actions/checkout@v4
       - name: ${{ matrix.config }}
@@ -188,6 +193,7 @@ jobs:
           path: |
             **/test-results.xml
             **/*.abilist
+            **/CMakeConfigureLog.yaml
             **/CMakeError.log
             **/CMakeOutput.log
             **/crash_diagnostics/*
@@ -230,6 +236,7 @@ jobs:
           path: |
             **/test-results.xml
             **/*.abilist
+            **/CMakeConfigureLog.yaml
             **/CMakeError.log
             **/CMakeOutput.log
             **/crash_diagnostics/*

bolt/lib/Core/BinaryFunction.cpp

@@ -2577,6 +2577,7 @@ struct CFISnapshot {
     case MCCFIInstruction::OpAdjustCfaOffset:
     case MCCFIInstruction::OpWindowSave:
     case MCCFIInstruction::OpNegateRAState:
+    case MCCFIInstruction::OpNegateRAStateWithPC:
     case MCCFIInstruction::OpLLVMDefAspaceCfa:
     case MCCFIInstruction::OpLabel:
       llvm_unreachable("unsupported CFI opcode");
@@ -2715,6 +2716,7 @@ struct CFISnapshotDiff : public CFISnapshot {
     case MCCFIInstruction::OpAdjustCfaOffset:
     case MCCFIInstruction::OpWindowSave:
     case MCCFIInstruction::OpNegateRAState:
+    case MCCFIInstruction::OpNegateRAStateWithPC:
     case MCCFIInstruction::OpLLVMDefAspaceCfa:
     case MCCFIInstruction::OpLabel:
       llvm_unreachable("unsupported CFI opcode");
@@ -2864,6 +2866,7 @@ BinaryFunction::unwindCFIState(int32_t FromState, int32_t ToState,
     case MCCFIInstruction::OpAdjustCfaOffset:
     case MCCFIInstruction::OpWindowSave:
     case MCCFIInstruction::OpNegateRAState:
+    case MCCFIInstruction::OpNegateRAStateWithPC:
     case MCCFIInstruction::OpLLVMDefAspaceCfa:
     case MCCFIInstruction::OpLabel:
       llvm_unreachable("unsupported CFI opcode");

bolt/lib/Core/HashUtilities.cpp

@@ -145,7 +145,7 @@ std::string hashBlockLoose(BinaryContext &BC, const BinaryBasicBlock &BB) {
       continue;
     }
 
-    std::string Mnemonic = BC.InstPrinter->getMnemonic(&Inst).first;
+    std::string Mnemonic = BC.InstPrinter->getMnemonic(Inst).first;
     llvm::erase_if(Mnemonic, [](unsigned char ch) { return std::isspace(ch); });
     Opcodes.insert(Mnemonic);
   }

bolt/test/X86/pre-aggregated-perf.test

@@ -11,13 +11,15 @@ REQUIRES: system-linux
 
 RUN: yaml2obj %p/Inputs/blarge.yaml &> %t.exe
 RUN: perf2bolt %t.exe -o %t --pa -p %p/Inputs/pre-aggregated.txt -w %t.new \
+RUN:   --show-density \
 RUN:   --profile-density-threshold=9 --profile-density-cutoff-hot=970000 \
 RUN:   --profile-use-dfs | FileCheck %s --check-prefix=CHECK-P2B
 
 CHECK-P2B: BOLT-INFO: 4 out of 7 functions in the binary (57.1%) have non-empty execution profile
 CHECK-P2B: BOLT-INFO: Functions with density >= 21.7 account for 97.00% total sample counts.
 
 RUN: perf2bolt %t.exe -o %t --pa -p %p/Inputs/pre-aggregated.txt -w %t.new \
+RUN:   --show-density \
 RUN:   --profile-density-cutoff-hot=970000 \
 RUN:   --profile-use-dfs 2>&1 | FileCheck %s --check-prefix=CHECK-WARNING
 

clang-tools-extra/clang-query/Query.cpp

@@ -44,7 +44,9 @@ bool HelpQuery::run(llvm::raw_ostream &OS, QuerySession &QS) const {
         "  set bind-root (true|false)        "
         "Set whether to bind the root matcher to \"root\".\n"
         "  set print-matcher (true|false)    "
-        "Set whether to print the current matcher,\n"
+        "Set whether to print the current matcher.\n"
+        "  set enable-profile (true|false)   "
+        "Set whether to enable matcher profiling.\n"
         "  set traversal <kind>              "
         "Set traversal kind of clang-query session. Available kinds are:\n"
         "    AsIs                            "
@@ -82,27 +84,53 @@ namespace {
 
 struct CollectBoundNodes : MatchFinder::MatchCallback {
   std::vector<BoundNodes> &Bindings;
-  CollectBoundNodes(std::vector<BoundNodes> &Bindings) : Bindings(Bindings) {}
+  StringRef Unit;
+  CollectBoundNodes(std::vector<BoundNodes> &Bindings, StringRef Unit)
+      : Bindings(Bindings), Unit(Unit) {}
   void run(const MatchFinder::MatchResult &Result) override {
     Bindings.push_back(Result.Nodes);
   }
+  StringRef getID() const override { return Unit; }
+};
+
+struct QueryProfiler {
+  llvm::StringMap<llvm::TimeRecord> Records;
+
+  ~QueryProfiler() {
+    llvm::TimerGroup TG("clang-query", "clang-query matcher profiling",
+                        Records);
+    TG.print(llvm::errs());
+    llvm::errs().flush();
+  }
 };
 
 } // namespace
 
 bool MatchQuery::run(llvm::raw_ostream &OS, QuerySession &QS) const {
   unsigned MatchCount = 0;
 
+  std::optional<QueryProfiler> Profiler;
+  if (QS.EnableProfile)
+    Profiler.emplace();
+
   for (auto &AST : QS.ASTs) {
-    MatchFinder Finder;
+    ast_matchers::MatchFinder::MatchFinderOptions FinderOptions;
+    std::optional<llvm::StringMap<llvm::TimeRecord>> Records;
+    if (QS.EnableProfile) {
+      Records.emplace();
+      FinderOptions.CheckProfiling.emplace(*Records);
+    }
+
+    MatchFinder Finder(FinderOptions);
     std::vector<BoundNodes> Matches;
     DynTypedMatcher MaybeBoundMatcher = Matcher;
     if (QS.BindRoot) {
       std::optional<DynTypedMatcher> M = Matcher.tryBind("root");
       if (M)
         MaybeBoundMatcher = *M;
     }
-    CollectBoundNodes Collect(Matches);
+    StringRef OrigSrcName = AST->getOriginalSourceFileName();
+    CollectBoundNodes Collect(Matches, OrigSrcName);
     if (!Finder.addDynamicMatcher(MaybeBoundMatcher, &Collect)) {
       OS << "Not a valid top-level matcher.\n";
       return false;
@@ -111,6 +139,8 @@ bool MatchQuery::run(llvm::raw_ostream &OS, QuerySession &QS) const {
     ASTContext &Ctx = AST->getASTContext();
     Ctx.getParentMapContext().setTraversalKind(QS.TK);
     Finder.matchAST(Ctx);
+    if (QS.EnableProfile)
+      Profiler->Records[OrigSrcName] += (*Records)[OrigSrcName];
 
     if (QS.PrintMatcher) {
       SmallVector<StringRef, 4> Lines;

clang-tools-extra/clang-query/QueryParser.cpp

@@ -182,6 +182,7 @@ enum ParsedQueryVariable {
   PQV_Output,
   PQV_BindRoot,
   PQV_PrintMatcher,
+  PQV_EnableProfile,
   PQV_Traversal
 };
 
@@ -285,6 +286,7 @@ QueryRef QueryParser::doParse() {
             .Case("output", PQV_Output)
             .Case("bind-root", PQV_BindRoot)
             .Case("print-matcher", PQV_PrintMatcher)
+            .Case("enable-profile", PQV_EnableProfile)
             .Case("traversal", PQV_Traversal)
             .Default(PQV_Invalid);
     if (VarStr.empty())
@@ -303,6 +305,9 @@ QueryRef QueryParser::doParse() {
     case PQV_PrintMatcher:
       Q = parseSetBool(&QuerySession::PrintMatcher);
       break;
+    case PQV_EnableProfile:
+      Q = parseSetBool(&QuerySession::EnableProfile);
+      break;
     case PQV_Traversal:
       Q = parseSetTraversalKind(&QuerySession::TK);
       break;

clang-tools-extra/clang-query/QuerySession.h

@@ -26,7 +26,7 @@ class QuerySession {
   QuerySession(llvm::ArrayRef<std::unique_ptr<ASTUnit>> ASTs)
       : ASTs(ASTs), PrintOutput(false), DiagOutput(true),
         DetailedASTOutput(false), BindRoot(true), PrintMatcher(false),
-        Terminate(false), TK(TK_AsIs) {}
+        EnableProfile(false), Terminate(false), TK(TK_AsIs) {}
 
   llvm::ArrayRef<std::unique_ptr<ASTUnit>> ASTs;
 
@@ -36,6 +36,7 @@ class QuerySession {
 
   bool BindRoot;
   bool PrintMatcher;
+  bool EnableProfile;
   bool Terminate;
 
   TraversalKind TK;

clang-tools-extra/clang-tidy/altera/IdDependentBackwardBranchCheck.cpp

@@ -78,33 +78,44 @@ void IdDependentBackwardBranchCheck::registerMatchers(MatchFinder *Finder) {
 
 IdDependentBackwardBranchCheck::IdDependencyRecord *
 IdDependentBackwardBranchCheck::hasIdDepVar(const Expr *Expression) {
+  if (!Expression)
+    return nullptr;
+
   if (const auto *Declaration = dyn_cast<DeclRefExpr>(Expression)) {
     // It is a DeclRefExpr, so check if it's an ID-dependent variable.
-    const auto *CheckVariable = dyn_cast<VarDecl>(Declaration->getDecl());
+    const auto *CheckVariable =
+        dyn_cast_if_present<VarDecl>(Declaration->getDecl());
+    if (!CheckVariable)
+      return nullptr;
     auto FoundVariable = IdDepVarsMap.find(CheckVariable);
     if (FoundVariable == IdDepVarsMap.end())
       return nullptr;
     return &(FoundVariable->second);
   }
   for (const auto *Child : Expression->children())
-    if (const auto *ChildExpression = dyn_cast<Expr>(Child))
+    if (const auto *ChildExpression = dyn_cast_if_present<Expr>(Child))
       if (IdDependencyRecord *Result = hasIdDepVar(ChildExpression))
         return Result;
   return nullptr;
 }
 
 IdDependentBackwardBranchCheck::IdDependencyRecord *
 IdDependentBackwardBranchCheck::hasIdDepField(const Expr *Expression) {
+  if (!Expression)
+    return nullptr;
+
   if (const auto *MemberExpression = dyn_cast<MemberExpr>(Expression)) {
     const auto *CheckField =
-        dyn_cast<FieldDecl>(MemberExpression->getMemberDecl());
+        dyn_cast_if_present<FieldDecl>(MemberExpression->getMemberDecl());
+    if (!CheckField)
+      return nullptr;
     auto FoundField = IdDepFieldsMap.find(CheckField);
     if (FoundField == IdDepFieldsMap.end())
       return nullptr;
     return &(FoundField->second);
   }
   for (const auto *Child : Expression->children())
-    if (const auto *ChildExpression = dyn_cast<Expr>(Child))
+    if (const auto *ChildExpression = dyn_cast_if_present<Expr>(Child))
       if (IdDependencyRecord *Result = hasIdDepField(ChildExpression))
         return Result;
   return nullptr;

clang-tools-extra/clang-tidy/bugprone/ReturnConstRefFromParameterCheck.cpp

@@ -7,6 +7,7 @@
 //===----------------------------------------------------------------------===//
 
 #include "ReturnConstRefFromParameterCheck.h"
+#include "clang/AST/Expr.h"
 #include "clang/ASTMatchers/ASTMatchFinder.h"
 #include "clang/ASTMatchers/ASTMatchers.h"
 
@@ -15,19 +16,24 @@ using namespace clang::ast_matchers;
 namespace clang::tidy::bugprone {
 
 void ReturnConstRefFromParameterCheck::registerMatchers(MatchFinder *Finder) {
+  const auto DRef = ignoringParens(
+      declRefExpr(
+          to(parmVarDecl(hasType(hasCanonicalType(
+                             qualType(lValueReferenceType(pointee(
+                                          qualType(isConstQualified()))))
+                                 .bind("type"))))
+                 .bind("param")))
+          .bind("dref"));
+  const auto Func =
+      functionDecl(hasReturnTypeLoc(loc(
+                       qualType(hasCanonicalType(equalsBoundNode("type"))))))
+          .bind("func");
+
+  Finder->addMatcher(returnStmt(hasReturnValue(DRef), hasAncestor(Func)), this);
   Finder->addMatcher(
-      returnStmt(
-          hasReturnValue(declRefExpr(
-              to(parmVarDecl(hasType(hasCanonicalType(
-                                 qualType(lValueReferenceType(pointee(
-                                              qualType(isConstQualified()))))
-                                     .bind("type"))))
-                     .bind("param")))),
-          hasAncestor(
-              functionDecl(hasReturnTypeLoc(loc(qualType(
-                               hasCanonicalType(equalsBoundNode("type"))))))
-                  .bind("func")))
-          .bind("ret"),
+      returnStmt(hasReturnValue(ignoringParens(conditionalOperator(
+          eachOf(hasTrueExpression(DRef), hasFalseExpression(DRef)),
+          hasAncestor(Func))))),
       this);
 }
 
@@ -85,8 +91,8 @@ void ReturnConstRefFromParameterCheck::check(
     const MatchFinder::MatchResult &Result) {
   const auto *FD = Result.Nodes.getNodeAs<FunctionDecl>("func");
   const auto *PD = Result.Nodes.getNodeAs<ParmVarDecl>("param");
-  const auto *R = Result.Nodes.getNodeAs<ReturnStmt>("ret");
-  const SourceRange Range = R->getRetValue()->getSourceRange();
+  const auto *DRef = Result.Nodes.getNodeAs<DeclRefExpr>("dref");
+  const SourceRange Range = DRef->getSourceRange();
   if (Range.isInvalid())
     return;
 

clang-tools-extra/clang-tidy/modernize/UseDesignatedInitializersCheck.cpp

@@ -80,9 +80,13 @@ unsigned getNumberOfDesignated(const InitListExpr *SyntacticInitList) {
   });
 }
 
-AST_MATCHER(CXXRecordDecl, isAggregate) { return Node.isAggregate(); }
+AST_MATCHER(CXXRecordDecl, isAggregate) {
+  return Node.hasDefinition() && Node.isAggregate();
+}
 
-AST_MATCHER(CXXRecordDecl, isPOD) { return Node.isPOD(); }
+AST_MATCHER(CXXRecordDecl, isPOD) {
+  return Node.hasDefinition() && Node.isPOD();
+}
 
 AST_MATCHER(InitListExpr, isFullyDesignated) {
   if (const InitListExpr *SyntacticForm =

clang-tools-extra/clang-tidy/readability/FunctionCognitiveComplexityCheck.cpp

@@ -126,7 +126,7 @@ struct CognitiveComplexity final {
   // Limit of 25 is the "upstream"'s default.
   static constexpr unsigned DefaultLimit = 25U;
 
-  // Based on the publicly-avaliable numbers for some big open-source projects
+  // Based on the publicly-available numbers for some big open-source projects
   // https://sonarcloud.io/projects?languages=c%2Ccpp&size=5   we can estimate:
   // value ~20 would result in no allocs for 98% of functions, ~12 for 96%, ~10
   // for 91%, ~8 for 88%, ~6 for 84%, ~4 for 77%, ~2 for 64%, and ~1 for 37%.