Merge branch 'main' into main

Author: cor3ntin

clang/docs/ReleaseNotes.rst

@@ -35,9 +35,6 @@ Potentially Breaking Changes
 ============================
 
 - The Objective-C ARC migrator (ARCMigrate) has been removed.
-- Fix missing diagnostics for uses of declarations when performing typename access,
-  such as when performing member access on a '[[deprecated]]' type alias.
-  (#GH58547)
 
 C/C++ Language Potentially Breaking Changes
 -------------------------------------------
@@ -241,6 +238,9 @@ Improvements to Clang's diagnostics
   as function arguments or return value respectively. Note that
   :doc:`ThreadSafetyAnalysis` still does not perform alias analysis. The
   feature will be default-enabled with ``-Wthread-safety`` in a future release.
+- The ``-Wsign-compare`` warning now treats expressions with bitwise not(~) and minus(-) as signed integers 
+  except for the case where the operand is an unsigned integer
+  and throws warning if they are compared with unsigned integers (##18878).
 
 - Improve the diagnostics for chained comparisons to report actual expressions and operators (#GH129069).
 
@@ -297,6 +297,9 @@ Bug Fixes to C++ Support
 - Clang now uses the parameter location for abbreviated function templates in ``extern "C"``. (#GH46386)
 - Clang will emit an error instead of crash when use co_await or co_yield in
   C++26 braced-init-list template parameter initialization. (#GH78426)
+- Fixes matching of nested template template parameters. (#GH130362)
+- Correctly diagnoses template template paramters which have a pack parameter
+  not in the last position.
 - Clang now correctly parses ``if constexpr`` expressions in immediate function context. (#GH123524)
 
 Bug Fixes to AST Handling

clang/include/clang/Sema/Sema.h

@@ -3168,13 +3168,6 @@ class Sema final : public SemaBase {
 
   DeclGroupPtrTy ConvertDeclToDeclGroup(Decl *Ptr, Decl *OwnedType = nullptr);
 
-  enum class DiagCtorKind { None, Implicit, Typename };
-  /// Returns the TypeDeclType for the given type declaration,
-  /// as ASTContext::getTypeDeclType would, but
-  /// performs the required semantic checks for name lookup of said entity.
-  QualType getTypeDeclType(DeclContext *LookupCtx, DiagCtorKind DCK,
-                           TypeDecl *TD, SourceLocation NameLoc);
-
   /// If the identifier refers to a type name within this scope,
   /// return the declaration of that type.
   ///
@@ -11363,14 +11356,16 @@ class Sema final : public SemaBase {
 
   /// The context in which we are checking a template parameter list.
   enum TemplateParamListContext {
-    TPC_ClassTemplate,
-    TPC_VarTemplate,
+    // For this context, Class, Variable, TypeAlias, and non-pack Template
+    // Template Parameters are treated uniformly.
+    TPC_Other,
+
     TPC_FunctionTemplate,
     TPC_ClassTemplateMember,
     TPC_FriendClassTemplate,
     TPC_FriendFunctionTemplate,
     TPC_FriendFunctionTemplateDefinition,
-    TPC_TypeAliasTemplate
+    TPC_TemplateTemplateParameterPack,
   };
 
   /// Checks the validity of a template parameter list, possibly

clang/lib/CodeGen/Targets/AMDGPU.cpp

@@ -614,6 +614,20 @@ void AMDGPUTargetCodeGenInfo::setCUDAKernelCallingConvention(
       FT, FT->getExtInfo().withCallingConv(CC_OpenCLKernel));
 }
 
+/// Return IR struct type for rtinfo struct in rocm-device-libs used for device
+/// enqueue.
+///
+/// ptr addrspace(1) kernel_object, i32 private_segment_size,
+/// i32 group_segment_size
+
+static llvm::StructType *
+getAMDGPURuntimeHandleType(llvm::LLVMContext &C,
+                           llvm::Type *KernelDescriptorPtrTy) {
+  llvm::Type *Int32 = llvm::Type::getInt32Ty(C);
+  return llvm::StructType::create(C, {KernelDescriptorPtrTy, Int32, Int32},
+                                  "block.runtime.handle.t");
+}
+
 /// Create an OpenCL kernel for an enqueued block.
 ///
 /// The type of the first argument (the block literal) is the struct type
@@ -653,23 +667,29 @@ llvm::Value *AMDGPUTargetCodeGenInfo::createEnqueuedBlockKernel(
     ArgNames.push_back(
         llvm::MDString::get(C, (Twine("local_arg") + Twine(I)).str()));
   }
-  std::string Name = Invoke->getName().str() + "_kernel";
+
+  llvm::Module &Mod = CGF.CGM.getModule();
+  const llvm::DataLayout &DL = Mod.getDataLayout();
+
+  llvm::Twine Name = Invoke->getName() + "_kernel";
   auto *FT = llvm::FunctionType::get(llvm::Type::getVoidTy(C), ArgTys, false);
+
+  // The kernel itself can be internal, the runtime does not directly access the
+  // kernel address (only the kernel descriptor).
   auto *F = llvm::Function::Create(FT, llvm::GlobalValue::InternalLinkage, Name,
-                                   &CGF.CGM.getModule());
+                                   &Mod);
   F->setCallingConv(llvm::CallingConv::AMDGPU_KERNEL);
 
   llvm::AttrBuilder KernelAttrs(C);
   // FIXME: The invoke isn't applying the right attributes either
   // FIXME: This is missing setTargetAttributes
   CGF.CGM.addDefaultFunctionDefinitionAttributes(KernelAttrs);
-  KernelAttrs.addAttribute("enqueued-block");
   F->addFnAttrs(KernelAttrs);
 
   auto IP = CGF.Builder.saveIP();
   auto *BB = llvm::BasicBlock::Create(C, "entry", F);
   Builder.SetInsertPoint(BB);
-  const auto BlockAlign = CGF.CGM.getDataLayout().getPrefTypeAlign(BlockTy);
+  const auto BlockAlign = DL.getPrefTypeAlign(BlockTy);
   auto *BlockPtr = Builder.CreateAlloca(BlockTy, nullptr);
   BlockPtr->setAlignment(BlockAlign);
   Builder.CreateAlignedStore(F->arg_begin(), BlockPtr, BlockAlign);
@@ -692,7 +712,39 @@ llvm::Value *AMDGPUTargetCodeGenInfo::createEnqueuedBlockKernel(
   if (CGF.CGM.getCodeGenOpts().EmitOpenCLArgMetadata)
     F->setMetadata("kernel_arg_name", llvm::MDNode::get(C, ArgNames));
 
-  return F;
+  llvm::StructType *HandleTy = getAMDGPURuntimeHandleType(
+      C, llvm::PointerType::get(C, DL.getDefaultGlobalsAddressSpace()));
+  llvm::Constant *RuntimeHandleInitializer =
+      llvm::ConstantAggregateZero::get(HandleTy);
+
+  llvm::Twine RuntimeHandleName = F->getName() + ".runtime.handle";
+
+  // The runtime needs access to the runtime handle as an external symbol. The
+  // runtime handle will need to be made external later, in
+  // AMDGPUExportOpenCLEnqueuedBlocks. The kernel itself has a hidden reference
+  // inside the runtime handle, and is not directly referenced.
+
+  // TODO: We would initialize the first field by declaring F->getName() + ".kd"
+  // to reference the kernel descriptor. The runtime wouldn't need to bother
+  // setting it. We would need to have a final symbol name though.
+  // TODO: Can we directly use an external symbol with getGlobalIdentifier?
+  auto *RuntimeHandle = new llvm::GlobalVariable(
+      Mod, HandleTy,
+      /*isConstant=*/true, llvm::GlobalValue::InternalLinkage,
+      /*Initializer=*/RuntimeHandleInitializer, RuntimeHandleName,
+      /*InsertBefore=*/nullptr, llvm::GlobalValue::NotThreadLocal,
+      DL.getDefaultGlobalsAddressSpace(),
+      /*isExternallyInitialized=*/true);
+
+  llvm::MDNode *HandleAsMD =
+      llvm::MDNode::get(C, llvm::ValueAsMetadata::get(RuntimeHandle));
+  F->setMetadata(llvm::LLVMContext::MD_associated, HandleAsMD);
+
+  RuntimeHandle->setSection(".amdgpu.kernel.runtime.handle");
+
+  CGF.CGM.addUsedGlobal(F);
+  CGF.CGM.addUsedGlobal(RuntimeHandle);
+  return RuntimeHandle;
 }
 
 void CodeGenModule::handleAMDGPUFlatWorkGroupSizeAttr(

clang/lib/Sema/SemaChecking.cpp

@@ -10620,6 +10620,42 @@ static std::optional<IntRange> TryGetExprRange(ASTContext &C, const Expr *E,
     case UO_AddrOf: // should be impossible
       return IntRange::forValueOfType(C, GetExprType(E));
 
+    case UO_Minus: {
+      if (E->getType()->isUnsignedIntegerType()) {
+        return TryGetExprRange(C, UO->getSubExpr(), MaxWidth, InConstantContext,
+                               Approximate);
+      }
+
+      std::optional<IntRange> SubRange = TryGetExprRange(
+          C, UO->getSubExpr(), MaxWidth, InConstantContext, Approximate);
+
+      if (!SubRange)
+        return std::nullopt;
+
+      // If the range was previously non-negative, we need an extra bit for the
+      // sign bit. If the range was not non-negative, we need an extra bit
+      // because the negation of the most-negative value is one bit wider than
+      // that value.
+      return IntRange(SubRange->Width + 1, false);
+    }
+
+    case UO_Not: {
+      if (E->getType()->isUnsignedIntegerType()) {
+        return TryGetExprRange(C, UO->getSubExpr(), MaxWidth, InConstantContext,
+                               Approximate);
+      }
+
+      std::optional<IntRange> SubRange = TryGetExprRange(
+          C, UO->getSubExpr(), MaxWidth, InConstantContext, Approximate);
+
+      if (!SubRange)
+        return std::nullopt;
+
+      // The width increments by 1 if the sub-expression cannot be negative
+      // since it now can be.
+      return IntRange(SubRange->Width + (int)SubRange->NonNegative, false);
+    }
+
     default:
       return TryGetExprRange(C, UO->getSubExpr(), MaxWidth, InConstantContext,
                              Approximate);

clang/lib/Sema/SemaDecl.cpp

@@ -139,26 +139,6 @@ class TypeNameValidatorCCC final : public CorrectionCandidateCallback {
 
 } // end anonymous namespace
 
-QualType Sema::getTypeDeclType(DeclContext *LookupCtx, DiagCtorKind DCK,
-                               TypeDecl *TD, SourceLocation NameLoc) {
-  auto *LookupRD = dyn_cast_or_null<CXXRecordDecl>(LookupCtx);
-  auto *FoundRD = dyn_cast<CXXRecordDecl>(TD);
-  if (DCK != DiagCtorKind::None && LookupRD && FoundRD &&
-      FoundRD->isInjectedClassName() &&
-      declaresSameEntity(LookupRD, cast<Decl>(FoundRD->getParent()))) {
-    Diag(NameLoc,
-         DCK == DiagCtorKind::Typename
-             ? diag::ext_out_of_line_qualified_id_type_names_constructor
-             : diag::err_out_of_line_qualified_id_type_names_constructor)
-        << TD->getIdentifier() << /*Type=*/1
-        << 0 /*if any keyword was present, it was 'typename'*/;
-  }
-
-  DiagnoseUseOfDecl(TD, NameLoc);
-  MarkAnyDeclReferenced(TD->getLocation(), TD, /*OdrUse=*/false);
-  return Context.getTypeDeclType(TD);
-}
-
 namespace {
 enum class UnqualifiedTypeNameLookupResult {
   NotFound,
@@ -315,11 +295,10 @@ ParsedType Sema::getTypeName(const IdentifierInfo &II, SourceLocation NameLoc,
                              bool IsClassTemplateDeductionContext,
                              ImplicitTypenameContext AllowImplicitTypename,
                              IdentifierInfo **CorrectedII) {
-  bool IsImplicitTypename = !isClassName && !IsCtorOrDtorName;
   // FIXME: Consider allowing this outside C++1z mode as an extension.
   bool AllowDeducedTemplate = IsClassTemplateDeductionContext &&
-                              getLangOpts().CPlusPlus17 && IsImplicitTypename &&
-                              !HasTrailingDot;
+                              getLangOpts().CPlusPlus17 && !IsCtorOrDtorName &&
+                              !isClassName && !HasTrailingDot;
 
   // Determine where we will perform name lookup.
   DeclContext *LookupCtx = nullptr;
@@ -343,9 +322,11 @@ ParsedType Sema::getTypeName(const IdentifierInfo &II, SourceLocation NameLoc,
         // refer to a member of an unknown specialization.
         // In C++2a, in several contexts a 'typename' is not required. Also
         // allow this as an extension.
+        if (AllowImplicitTypename == ImplicitTypenameContext::No &&
+            !isClassName && !IsCtorOrDtorName)
+          return nullptr;
+        bool IsImplicitTypename = !isClassName && !IsCtorOrDtorName;
         if (IsImplicitTypename) {
-          if (AllowImplicitTypename == ImplicitTypenameContext::No)
-            return nullptr;
           SourceLocation QualifiedLoc = SS->getRange().getBegin();
           if (getLangOpts().CPlusPlus20)
             Diag(QualifiedLoc, diag::warn_cxx17_compat_implicit_typename);
@@ -534,10 +515,18 @@ ParsedType Sema::getTypeName(const IdentifierInfo &II, SourceLocation NameLoc,
     // C++ [class.qual]p2: A lookup that would find the injected-class-name
     // instead names the constructors of the class, except when naming a class.
     // This is ill-formed when we're not actually forming a ctor or dtor name.
-    T = getTypeDeclType(LookupCtx,
-                        IsImplicitTypename ? DiagCtorKind::Implicit
-                                           : DiagCtorKind::None,
-                        TD, NameLoc);
+    auto *LookupRD = dyn_cast_or_null<CXXRecordDecl>(LookupCtx);
+    auto *FoundRD = dyn_cast<CXXRecordDecl>(TD);
+    if (!isClassName && !IsCtorOrDtorName && LookupRD && FoundRD &&
+        FoundRD->isInjectedClassName() &&
+        declaresSameEntity(LookupRD, cast<Decl>(FoundRD->getParent())))
+      Diag(NameLoc, diag::err_out_of_line_qualified_id_type_names_constructor)
+          << &II << /*Type*/1;
+
+    DiagnoseUseOfDecl(IIDecl, NameLoc);
+
+    T = Context.getTypeDeclType(TD);
+    MarkAnyDeclReferenced(TD->getLocation(), TD, /*OdrUse=*/false);
   } else if (ObjCInterfaceDecl *IDecl = dyn_cast<ObjCInterfaceDecl>(IIDecl)) {
     (void)DiagnoseUseOfDecl(IDecl, NameLoc);
     if (!HasTrailingDot)
@@ -8165,7 +8154,7 @@ NamedDecl *Sema::ActOnVariableDeclarator(
               (D.getCXXScopeSpec().isSet() && DC && DC->isRecord() &&
                DC->isDependentContext())
                   ? TPC_ClassTemplateMember
-                  : TPC_VarTemplate))
+                  : TPC_Other))
         NewVD->setInvalidDecl();
 
       // If we are providing an explicit specialization of a static variable

clang/lib/Sema/SemaDeclCXX.cpp

@@ -13586,7 +13586,7 @@ Decl *Sema::ActOnAliasDeclaration(Scope *S, AccessSpecifier AS,
     // Merge any previous default template arguments into our parameters,
     // and check the parameter list.
     if (CheckTemplateParameterList(TemplateParams, OldTemplateParams,
-                                   TPC_TypeAliasTemplate))
+                                   TPC_Other))
       return nullptr;
 
     TypeAliasTemplateDecl *NewDecl =