Manually merged main:a88f4f1962b4 into amd-gfx:bc0af40b24d3

Local branch amd-gfx bc0af40 [AMDGPU] Prepare waterfall support for upstream changes (llvm#876)
Remote branch main a88f4f1 AMDGPU: Fix a test typo reading a partially undefined vectorMerge commit 'a88f4f1962b4' into merge-candidate

Author: dstutt

.github/workflows/release-binaries.yml

@@ -142,7 +142,7 @@ jobs:
             # 2-3 hours to build on macOS, much slower than on Linux.
             # The long build time causes the release build to time out on x86_64,
             # so we need to disable flang there.
-            target_cmake_flags="$target_cmake_flags -DLLVM_RELEASE_ENABLE_PROJECTS='clang;lld;lldb;clang-tools-extra;bolt;polly;mlir'"
+            target_cmake_flags="$target_cmake_flags -DLLVM_RELEASE_ENABLE_PROJECTS='clang;lld;lldb;clang-tools-extra;polly;mlir'"
           fi
           target_cmake_flags="$target_cmake_flags -DBOOTSTRAP_BOOTSTRAP_DARWIN_osx_ARCHS=$arches -DBOOTSTRAP_BOOTSTRAP_DARWIN_osx_BUILTIN_ARCHS=$arches"
         fi

bolt/lib/Core/BinaryFunction.cpp

@@ -15,6 +15,7 @@
 #include "bolt/Core/DynoStats.h"
 #include "bolt/Core/HashUtilities.h"
 #include "bolt/Core/MCPlusBuilder.h"
+#include "bolt/Utils/CommandLineOpts.h"
 #include "bolt/Utils/NameResolver.h"
 #include "bolt/Utils/NameShortener.h"
 #include "bolt/Utils/Utils.h"
@@ -1753,8 +1754,8 @@ void BinaryFunction::postProcessEntryPoints() {
     // In non-relocation mode there's potentially an external undetectable
     // reference to the entry point and hence we cannot move this entry
     // point. Optimizing without moving could be difficult.
-    // In BAT mode, register any known entry points for CFG construction.
-    if (!BC.HasRelocations && !BC.HasBATSection)
+    // In aggregation, register any known entry points for CFG construction.
+    if (!BC.HasRelocations && !opts::AggregateOnly)
       setSimple(false);
 
     const uint32_t Offset = KV.first;

bolt/lib/Profile/DataAggregator.cpp

@@ -831,9 +831,10 @@ bool DataAggregator::doTrace(const LBREntry &First, const LBREntry &Second,
     ParentFunc = FromFunc;
   ParentFunc->SampleCountInBytes += Count * (Second.From - First.To);
 
+  const uint64_t FuncAddress = FromFunc->getAddress();
   std::optional<BoltAddressTranslation::FallthroughListTy> FTs =
-      BAT ? BAT->getFallthroughsInTrace(FromFunc->getAddress(), First.To,
-                                        Second.From)
+      BAT && BAT->isBATFunction(FuncAddress)
+          ? BAT->getFallthroughsInTrace(FuncAddress, First.To, Second.From)
           : getFallthroughsInTrace(*FromFunc, First, Second, Count);
   if (!FTs) {
     LLVM_DEBUG(

bolt/test/X86/bolt-address-translation-yaml.test

@@ -61,6 +61,11 @@ YAML-BAT-CHECK-NEXT:   - bid:   0
 YAML-BAT-CHECK-NEXT:     insns: 26
 YAML-BAT-CHECK-NEXT:     hash:  0xA900AE79CFD40000
 YAML-BAT-CHECK-NEXT:     succ:  [ { bid: 3, cnt: 0 }, { bid: 1, cnt: 0 } ]
+# Check fallthroughs in non-BAT function
+YAML-BAT-CHECK-NEXT:   - bid:   27
+YAML-BAT-CHECK-NEXT:     insns: 3
+YAML-BAT-CHECK-NEXT:     hash:  0x30A1EBA77A903F0
+YAML-BAT-CHECK-NEXT:     succ:  [ { bid: 28, cnt: 1 } ]
 # Calls from no-BAT to BAT function
 YAML-BAT-CHECK:        - bid:   28
 YAML-BAT-CHECK-NEXT:     insns: 13

bolt/test/X86/entry-point-fallthru.s

@@ -0,0 +1,24 @@
+## Checks that fallthroughs spanning entry points are accepted in aggregation
+## mode.
+
+# RUN: llvm-mc -filetype=obj -triple x86_64-unknown-unknown %s -o %t.o
+# RUN: ld.lld %t.o -o %t
+# RUN: link_fdata %s %t %t.preagg PREAGG
+# RUN: perf2bolt %t -p %t.preagg --pa -o %t.fdata | FileCheck %s
+# CHECK: traces mismatching disassembled function contents: 0
+
+	.globl main
+main:
+	.cfi_startproc
+	vmovaps %zmm31,%zmm3
+
+next:
+	add    $0x4,%r9
+	add    $0x40,%r10
+	dec    %r14
+Ljmp:
+	jne    main
+# PREAGG: T #Ljmp# #main# #Ljmp# 1
+	ret
+	.cfi_endproc
+.size main,.-main

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

@@ -90,6 +90,7 @@
 #include "UndelegatedConstructorCheck.h"
 #include "UnhandledExceptionAtNewCheck.h"
 #include "UnhandledSelfAssignmentCheck.h"
+#include "UnintendedCharOstreamOutputCheck.h"
 #include "UniquePtrArrayMismatchCheck.h"
 #include "UnsafeFunctionsCheck.h"
 #include "UnusedLocalNonTrivialVariableCheck.h"
@@ -147,6 +148,8 @@ class BugproneModule : public ClangTidyModule {
         "bugprone-incorrect-enable-if");
     CheckFactories.registerCheck<IncorrectEnableSharedFromThisCheck>(
         "bugprone-incorrect-enable-shared-from-this");
+    CheckFactories.registerCheck<UnintendedCharOstreamOutputCheck>(
+        "bugprone-unintended-char-ostream-output");
     CheckFactories.registerCheck<ReturnConstRefFromParameterCheck>(
         "bugprone-return-const-ref-from-parameter");
     CheckFactories.registerCheck<SwitchMissingDefaultCaseCheck>(

clang-tools-extra/clang-tidy/bugprone/CMakeLists.txt

@@ -29,6 +29,7 @@ add_clang_library(clangTidyBugproneModule STATIC
   InaccurateEraseCheck.cpp
   IncorrectEnableIfCheck.cpp
   IncorrectEnableSharedFromThisCheck.cpp
+  UnintendedCharOstreamOutputCheck.cpp
   ReturnConstRefFromParameterCheck.cpp
   SuspiciousStringviewDataUsageCheck.cpp
   SwitchMissingDefaultCaseCheck.cpp

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

@@ -0,0 +1,91 @@
+//===--- UnintendedCharOstreamOutputCheck.cpp - clang-tidy ----------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#include "UnintendedCharOstreamOutputCheck.h"
+#include "clang/AST/Type.h"
+#include "clang/ASTMatchers/ASTMatchFinder.h"
+#include "clang/ASTMatchers/ASTMatchers.h"
+#include "clang/Basic/Diagnostic.h"
+#include "clang/Tooling/FixIt.h"
+
+using namespace clang::ast_matchers;
+
+namespace clang::tidy::bugprone {
+
+namespace {
+
+// check if the type is unsigned char or signed char
+AST_MATCHER(Type, isNumericChar) {
+  return Node.isSpecificBuiltinType(BuiltinType::SChar) ||
+         Node.isSpecificBuiltinType(BuiltinType::UChar);
+}
+
+// check if the type is char
+AST_MATCHER(Type, isChar) {
+  return Node.isSpecificBuiltinType(BuiltinType::Char_S) ||
+         Node.isSpecificBuiltinType(BuiltinType::Char_U);
+}
+
+} // namespace
+
+UnintendedCharOstreamOutputCheck::UnintendedCharOstreamOutputCheck(
+    StringRef Name, ClangTidyContext *Context)
+    : ClangTidyCheck(Name, Context), CastTypeName(Options.get("CastTypeName")) {
+}
+void UnintendedCharOstreamOutputCheck::storeOptions(
+    ClangTidyOptions::OptionMap &Opts) {
+  if (CastTypeName.has_value())
+    Options.store(Opts, "CastTypeName", CastTypeName.value());
+}
+
+void UnintendedCharOstreamOutputCheck::registerMatchers(MatchFinder *Finder) {
+  auto BasicOstream =
+      cxxRecordDecl(hasName("::std::basic_ostream"),
+                    // only basic_ostream<char, Traits> has overload operator<<
+                    // with char / unsigned char / signed char
+                    classTemplateSpecializationDecl(
+                        hasTemplateArgument(0, refersToType(isChar()))));
+  Finder->addMatcher(
+      cxxOperatorCallExpr(
+          hasOverloadedOperatorName("<<"),
+          hasLHS(hasType(hasUnqualifiedDesugaredType(
+              recordType(hasDeclaration(cxxRecordDecl(
+                  anyOf(BasicOstream, isDerivedFrom(BasicOstream)))))))),
+          hasRHS(hasType(hasUnqualifiedDesugaredType(isNumericChar()))))
+          .bind("x"),
+      this);
+}
+
+void UnintendedCharOstreamOutputCheck::check(
+    const MatchFinder::MatchResult &Result) {
+  const auto *Call = Result.Nodes.getNodeAs<CXXOperatorCallExpr>("x");
+  const Expr *Value = Call->getArg(1);
+  const SourceRange SourceRange = Value->getSourceRange();
+
+  DiagnosticBuilder Builder =
+      diag(Call->getOperatorLoc(),
+           "%0 passed to 'operator<<' outputs as character instead of integer. "
+           "cast to 'unsigned int' to print numeric value or cast to 'char' to "
+           "print as character")
+      << Value->getType() << SourceRange;
+
+  QualType T = Value->getType();
+  const Type *UnqualifiedDesugaredType = T->getUnqualifiedDesugaredType();
+
+  llvm::StringRef CastType = CastTypeName.value_or(
+      UnqualifiedDesugaredType->isSpecificBuiltinType(BuiltinType::SChar)
+          ? "int"
+          : "unsigned int");
+
+  Builder << FixItHint::CreateReplacement(
+      SourceRange, ("static_cast<" + CastType + ">(" +
+                    tooling::fixit::getText(*Value, *Result.Context) + ")")
+                       .str());
+}
+
+} // namespace clang::tidy::bugprone

clang-tools-extra/clang-tidy/bugprone/UnintendedCharOstreamOutputCheck.h

@@ -0,0 +1,38 @@
+//===--- UnintendedCharOstreamOutputCheck.h - clang-tidy --------*- C++ -*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_CLANG_TOOLS_EXTRA_CLANG_TIDY_BUGPRONE_UNINTENDEDCHAROSTREAMOUTPUTCHECK_H
+#define LLVM_CLANG_TOOLS_EXTRA_CLANG_TIDY_BUGPRONE_UNINTENDEDCHAROSTREAMOUTPUTCHECK_H
+
+#include "../ClangTidyCheck.h"
+#include <optional>
+
+namespace clang::tidy::bugprone {
+
+/// Finds unintended character output from `unsigned char` and `signed char` to
+/// an ostream.
+///
+/// For the user-facing documentation see:
+/// http://clang.llvm.org/extra/clang-tidy/checks/bugprone/unintended-char-ostream-output.html
+class UnintendedCharOstreamOutputCheck : public ClangTidyCheck {
+public:
+  UnintendedCharOstreamOutputCheck(StringRef Name, ClangTidyContext *Context);
+  void storeOptions(ClangTidyOptions::OptionMap &Opts) override;
+  void registerMatchers(ast_matchers::MatchFinder *Finder) override;
+  void check(const ast_matchers::MatchFinder::MatchResult &Result) override;
+  bool isLanguageVersionSupported(const LangOptions &LangOpts) const override {
+    return LangOpts.CPlusPlus;
+  }
+
+private:
+  const std::optional<StringRef> CastTypeName;
+};
+
+} // namespace clang::tidy::bugprone
+
+#endif // LLVM_CLANG_TOOLS_EXTRA_CLANG_TIDY_BUGPRONE_UNINTENDEDCHAROSTREAMOUTPUTCHECK_H

clang-tools-extra/clang-tidy/performance/MoveConstArgCheck.cpp

@@ -44,6 +44,10 @@ void MoveConstArgCheck::registerMatchers(MatchFinder *Finder) {
                unless(isInTemplateInstantiation()))
           .bind("call-move");
 
+  // Match ternary expressions where either branch contains std::move
+  auto TernaryWithMoveMatcher =
+      conditionalOperator(hasDescendant(MoveCallMatcher));
+
   Finder->addMatcher(
       expr(anyOf(
           castExpr(hasSourceExpression(MoveCallMatcher)),
@@ -58,13 +62,15 @@ void MoveConstArgCheck::registerMatchers(MatchFinder *Finder) {
       qualType(rValueReferenceType()).bind("invocation-parm-type");
   // Matches respective ParmVarDecl for a CallExpr or CXXConstructExpr.
   auto ArgumentWithParamMatcher = forEachArgumentWithParam(
-      MoveCallMatcher, parmVarDecl(anyOf(hasType(ConstTypeParmMatcher),
-                                         hasType(RValueTypeParmMatcher)))
-                           .bind("invocation-parm"));
+      anyOf(MoveCallMatcher, TernaryWithMoveMatcher),
+      parmVarDecl(
+          anyOf(hasType(ConstTypeParmMatcher), hasType(RValueTypeParmMatcher)))
+          .bind("invocation-parm"));
   // Matches respective types of arguments for a CallExpr or CXXConstructExpr
   // and it works on calls through function pointers as well.
   auto ArgumentWithParamTypeMatcher = forEachArgumentWithParamType(
-      MoveCallMatcher, anyOf(ConstTypeParmMatcher, RValueTypeParmMatcher));
+      anyOf(MoveCallMatcher, TernaryWithMoveMatcher),
+      anyOf(ConstTypeParmMatcher, RValueTypeParmMatcher));
 
   Finder->addMatcher(
       invocation(anyOf(ArgumentWithParamMatcher, ArgumentWithParamTypeMatcher))