Merge from 'main' to 'sycl-web' (intel#46)

  CONFLICT (content): Merge conflict in clang/tools/clang-offload-wrapper/ClangOffloadWrapper.cpp
  CONFLICT (content): Merge conflict in clang/test/Driver/clang-offload-wrapper.c

Author: speryt

.mailmap

@@ -32,4 +32,4 @@ Jon Roelofs <[email protected]> <[email protected]>
 Jon Roelofs <[email protected]> <[email protected]>
 LLVM GN Syncbot <[email protected]>
 Martin Storsjö <[email protected]>
-Saleem Abdulrasool <[email protected]> <[email protected]>
+Saleem Abdulrasool <[email protected]>

clang-tools-extra/clangd/CMakeLists.txt

@@ -83,6 +83,7 @@ add_clang_library(clangDaemon
   HeaderSourceSwitch.cpp
   HeuristicResolver.cpp
   Hover.cpp
+  IncludeCleaner.cpp
   IncludeFixer.cpp
   InlayHints.cpp
   JSONTransport.cpp

clang-tools-extra/clangd/IncludeCleaner.cpp

@@ -0,0 +1,112 @@
+//===--- IncludeCleaner.cpp - Unused/Missing Headers Analysis ---*- 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
+//
+//===----------------------------------------------------------------------===//
+
+#include "IncludeCleaner.h"
+#include "support/Logger.h"
+#include "clang/AST/RecursiveASTVisitor.h"
+#include "clang/Basic/SourceLocation.h"
+
+namespace clang {
+namespace clangd {
+namespace {
+
+/// Crawler traverses the AST and feeds in the locations of (sometimes
+/// implicitly) used symbols into \p Result.
+class ReferencedLocationCrawler
+    : public RecursiveASTVisitor<ReferencedLocationCrawler> {
+public:
+  ReferencedLocationCrawler(ReferencedLocations &Result) : Result(Result) {}
+
+  bool VisitDeclRefExpr(DeclRefExpr *DRE) {
+    add(DRE->getDecl());
+    add(DRE->getFoundDecl());
+    return true;
+  }
+
+  bool VisitMemberExpr(MemberExpr *ME) {
+    add(ME->getMemberDecl());
+    add(ME->getFoundDecl().getDecl());
+    return true;
+  }
+
+  bool VisitTagType(TagType *TT) {
+    add(TT->getDecl());
+    return true;
+  }
+
+  bool VisitCXXConstructExpr(CXXConstructExpr *CCE) {
+    add(CCE->getConstructor());
+    return true;
+  }
+
+  bool VisitTemplateSpecializationType(TemplateSpecializationType *TST) {
+    if (isNew(TST)) {
+      add(TST->getTemplateName().getAsTemplateDecl()); // Primary template.
+      add(TST->getAsCXXRecordDecl());                  // Specialization
+    }
+    return true;
+  }
+
+  bool VisitTypedefType(TypedefType *TT) {
+    add(TT->getDecl());
+    return true;
+  }
+
+  // Consider types of any subexpression used, even if the type is not named.
+  // This is helpful in getFoo().bar(), where Foo must be complete.
+  // FIXME(kirillbobyrev): Should we tweak this? It may not be desirable to
+  // consider types "used" when they are not directly spelled in code.
+  bool VisitExpr(Expr *E) {
+    TraverseType(E->getType());
+    return true;
+  }
+
+  bool TraverseType(QualType T) {
+    if (isNew(T.getTypePtrOrNull())) { // don't care about quals
+      Base::TraverseType(T);
+    }
+    return true;
+  }
+
+  bool VisitUsingDecl(UsingDecl *D) {
+    for (const auto *Shadow : D->shadows()) {
+      add(Shadow->getTargetDecl());
+    }
+    return true;
+  }
+
+private:
+  using Base = RecursiveASTVisitor<ReferencedLocationCrawler>;
+
+  void add(const Decl *D) {
+    if (!D || !isNew(D->getCanonicalDecl())) {
+      return;
+    }
+    for (const Decl *Redecl : D->redecls()) {
+      Result.insert(Redecl->getLocation());
+    }
+  }
+
+  bool isNew(const void *P) { return P && Visited.insert(P).second; }
+
+  ReferencedLocations &Result;
+  llvm::DenseSet<const void *> Visited;
+};
+
+} // namespace
+
+ReferencedLocations findReferencedLocations(ParsedAST &AST) {
+  ReferencedLocations Result;
+  ReferencedLocationCrawler Crawler(Result);
+  Crawler.TraverseAST(AST.getASTContext());
+  // FIXME(kirillbobyrev): Handle macros.
+  return Result;
+}
+
+} // namespace clangd
+} // namespace clang

clang-tools-extra/clangd/IncludeCleaner.h

@@ -0,0 +1,52 @@
+//===--- IncludeCleaner.h - Unused/Missing Headers Analysis -----*- 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
+//
+//===----------------------------------------------------------------------===//
+///
+/// \file
+/// Include Cleaner is clangd functionality for providing diagnostics for misuse
+/// of transitive headers and unused includes. It is inspired by
+/// Include-What-You-Use tool (https://include-what-you-use.org/). Our goal is
+/// to provide useful warnings in most popular scenarios but not 1:1 exact
+/// feature compatibility.
+///
+/// FIXME(kirillbobyrev): Add support for IWYU pragmas.
+/// FIXME(kirillbobyrev): Add support for standard library headers.
+///
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_CLANG_TOOLS_EXTRA_CLANGD_INCLUDE_CLEANER_H
+#define LLVM_CLANG_TOOLS_EXTRA_CLANGD_INCLUDE_CLEANER_H
+
+#include "Headers.h"
+#include "ParsedAST.h"
+#include "clang/Basic/SourceLocation.h"
+#include "llvm/ADT/DenseSet.h"
+
+namespace clang {
+namespace clangd {
+
+using ReferencedLocations = llvm::DenseSet<SourceLocation>;
+/// Finds locations of all symbols used in the main file.
+///
+/// Uses RecursiveASTVisitor to go through main file AST and computes all the
+/// locations used symbols are coming from. Returned locations may be macro
+/// expansions, and are not resolved to their spelling/expansion location. These
+/// locations are later used to determine which headers should be marked as
+/// "used" and "directly used".
+///
+/// We use this to compute unused headers, so we:
+///
+/// - cover the whole file in a single traversal for efficiency
+/// - don't attempt to describe where symbols were referenced from in
+///   ambiguous cases (e.g. implicitly used symbols, multiple declarations)
+/// - err on the side of reporting all possible locations
+ReferencedLocations findReferencedLocations(ParsedAST &AST);
+
+} // namespace clangd
+} // namespace clang
+
+#endif // LLVM_CLANG_TOOLS_EXTRA_CLANGD_INCLUDE_CLEANER_H

clang-tools-extra/clangd/unittests/CMakeLists.txt

@@ -58,6 +58,7 @@ add_unittest(ClangdUnitTests ClangdTests
   HeadersTests.cpp
   HeaderSourceSwitchTests.cpp
   HoverTests.cpp
+  IncludeCleanerTests.cpp
   IndexActionTests.cpp
   IndexTests.cpp
   InlayHintTests.cpp

clang-tools-extra/clangd/unittests/IncludeCleanerTests.cpp

@@ -0,0 +1,136 @@
+//===--- IncludeCleanerTests.cpp --------------------------------*- 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
+//
+//===----------------------------------------------------------------------===//
+
+#include "Annotations.h"
+#include "IncludeCleaner.h"
+#include "TestTU.h"
+#include "gmock/gmock.h"
+#include "gtest/gtest.h"
+
+namespace clang {
+namespace clangd {
+namespace {
+
+TEST(IncludeCleaner, ReferencedLocations) {
+  struct TestCase {
+    std::string HeaderCode;
+    std::string MainCode;
+  };
+  TestCase Cases[] = {
+      // DeclRefExpr
+      {
+          "int ^x();",
+          "int y = x();",
+      },
+      // RecordDecl
+      {
+          "class ^X;",
+          "X *y;",
+      },
+      // TypedefType and UsingDecls
+      {
+          "using ^Integer = int;",
+          "Integer x;",
+      },
+      {
+          "namespace ns { struct ^X; struct ^X {}; }",
+          "using ns::X;",
+      },
+      {
+          "namespace ns { struct X; struct X {}; }",
+          "using namespace ns;",
+      },
+      {
+          "struct ^A {}; using B = A; using ^C = B;",
+          "C a;",
+      },
+      {
+          "typedef bool ^Y; template <typename T> struct ^X {};",
+          "X<Y> x;",
+      },
+      {
+          "struct Foo; struct ^Foo{}; typedef Foo ^Bar;",
+          "Bar b;",
+      },
+      // MemberExpr
+      {
+          "struct ^X{int ^a;}; X ^foo();",
+          "int y = foo().a;",
+      },
+      // Expr (type is traversed)
+      {
+          "class ^X{}; X ^foo();",
+          "auto bar() { return foo(); }",
+      },
+      // Redecls
+      {
+          "class ^X; class ^X{}; class ^X;",
+          "X *y;",
+      },
+      // Constructor
+      {
+          "struct ^X { ^X(int) {} int ^foo(); };",
+          "auto x = X(42); auto y = x.foo();",
+      },
+      // Static function
+      {
+          "struct ^X { static bool ^foo(); }; bool X::^foo() {}",
+          "auto b = X::foo();",
+      },
+      // TemplateRecordDecl
+      {
+          "template <typename> class ^X;",
+          "X<int> *y;",
+      },
+      // Type name not spelled out in code
+      {
+          "class ^X{}; X ^getX();",
+          "auto x = getX();",
+      },
+      // Enums
+      {
+          "enum ^Color { ^Red = 42, Green = 9000};",
+          "int MyColor = Red;",
+      },
+      {
+          "struct ^X { enum ^Language { ^CXX = 42, Python = 9000}; };",
+          "int Lang = X::CXX;",
+      },
+      {
+          // When a type is resolved via a using declaration, the
+          // UsingShadowDecl is not referenced in the AST.
+          // Compare to TypedefType, or DeclRefExpr::getFoundDecl().
+          //                                 ^
+          "namespace ns { class ^X; }; using ns::X;",
+          "X *y;",
+      }};
+  for (const TestCase &T : Cases) {
+    TestTU TU;
+    TU.Code = T.MainCode;
+    Annotations Header(T.HeaderCode);
+    TU.HeaderCode = Header.code().str();
+    auto AST = TU.build();
+
+    std::vector<Position> Points;
+    for (const auto &Loc : findReferencedLocations(AST)) {
+      if (AST.getSourceManager().getBufferName(Loc).endswith(
+              TU.HeaderFilename)) {
+        Points.push_back(offsetToPosition(
+            TU.HeaderCode, AST.getSourceManager().getFileOffset(Loc)));
+      }
+    }
+    llvm::sort(Points);
+
+    EXPECT_EQ(Points, Header.points()) << T.HeaderCode << "\n---\n"
+                                       << T.MainCode;
+  }
+}
+
+} // namespace
+} // namespace clangd
+} // namespace clang

clang/include/clang/Basic/CharInfo.h

@@ -43,6 +43,11 @@ LLVM_READNONE inline bool isASCII(char c) {
   return static_cast<unsigned char>(c) <= 127;
 }
 
+LLVM_READNONE inline bool isASCII(unsigned char c) { return c <= 127; }
+
+/// Returns true if this is an ASCII character.
+LLVM_READNONE inline bool isASCII(uint32_t c) { return c <= 127; }
+
 /// Returns true if this is a valid first character of a C identifier,
 /// which is [a-zA-Z_].
 LLVM_READONLY inline bool isIdentifierHead(unsigned char c,

clang/include/clang/Basic/DiagnosticLexKinds.td

@@ -113,8 +113,10 @@ def warn_four_char_character_literal : Warning<
 // Unicode and UCNs
 def err_invalid_utf8 : Error<
   "source file is not valid UTF-8">;
-def err_non_ascii : Error<
-  "non-ASCII characters are not allowed outside of literals and identifiers">;
+def err_character_not_allowed : Error<
+  "unexpected character <U+%0>">;
+def err_character_not_allowed_identifier : Error<
+  "character <U+%0> not allowed %select{in|at the start of}1 an identifier">;
 def ext_unicode_whitespace : ExtWarn<
   "treating Unicode character as whitespace">,
   InGroup<DiagGroup<"unicode-whitespace">>;
@@ -150,9 +152,6 @@ def warn_c99_compat_unicode_id : Warning<
   "%select{using this character in an identifier|starting an identifier with "
   "this character}0 is incompatible with C99">,
   InGroup<C99Compat>, DefaultIgnore;
-def warn_cxx98_compat_unicode_id : Warning<
-  "using this character in an identifier is incompatible with C++98">,
-  InGroup<CXX98Compat>, DefaultIgnore;
 
 def warn_cxx98_compat_literal_ucn_escape_basic_scs : Warning<
   "specifying character '%0' with a universal character name "

clang/include/clang/Basic/LangStandards.def

@@ -180,19 +180,26 @@ LANGSTANDARD(opencl20, "cl2.0",
 LANGSTANDARD(opencl30, "cl3.0",
              OpenCL, "OpenCL 3.0",
              LineComment | C99 | Digraphs | HexFloat | OpenCL)
+
 LANGSTANDARD(openclcpp10, "clc++1.0",
              OpenCL, "C++ for OpenCL 1.0",
              LineComment | CPlusPlus | CPlusPlus11 | CPlusPlus14 | CPlusPlus17 |
              Digraphs | HexFloat | OpenCL)
 LANGSTANDARD_ALIAS(openclcpp10, "clc++")
 
+LANGSTANDARD(openclcpp2021, "clc++2021",
+             OpenCL, "C++ for OpenCL 2021",
+             LineComment | CPlusPlus | CPlusPlus11 | CPlusPlus14 | CPlusPlus17 |
+             Digraphs | HexFloat | OpenCL)
+
 LANGSTANDARD_ALIAS_DEPR(opencl10, "CL")
 LANGSTANDARD_ALIAS_DEPR(opencl11, "CL1.1")
 LANGSTANDARD_ALIAS_DEPR(opencl12, "CL1.2")
 LANGSTANDARD_ALIAS_DEPR(opencl20, "CL2.0")
 LANGSTANDARD_ALIAS_DEPR(opencl30, "CL3.0")
 LANGSTANDARD_ALIAS_DEPR(openclcpp10, "CLC++")
 LANGSTANDARD_ALIAS_DEPR(openclcpp10, "CLC++1.0")
+LANGSTANDARD_ALIAS_DEPR(openclcpp2021, "CLC++2021")
 
 // CUDA
 LANGSTANDARD(cuda, "cuda", CUDA, "NVIDIA CUDA(tm)",

clang/include/clang/Driver/Options.td

@@ -887,7 +887,7 @@ def cl_no_signed_zeros : Flag<["-"], "cl-no-signed-zeros">, Group<opencl_Group>,
   MarshallingInfoFlag<LangOpts<"CLNoSignedZero">>;
 def cl_std_EQ : Joined<["-"], "cl-std=">, Group<opencl_Group>, Flags<[CC1Option]>,
   HelpText<"OpenCL language standard to compile for.">,
-  Values<"cl,CL,cl1.0,CL1.0,cl1.1,CL1.1,cl1.2,CL1.2,cl2.0,CL2.0,cl3.0,CL3.0,clc++,CLC++,clc++1.0,CLC++1.0">;
+  Values<"cl,CL,cl1.0,CL1.0,cl1.1,CL1.1,cl1.2,CL1.2,cl2.0,CL2.0,cl3.0,CL3.0,clc++,CLC++,clc++1.0,CLC++1.0,clc++2021,CLC++2021">;
 def cl_denorms_are_zero : Flag<["-"], "cl-denorms-are-zero">, Group<opencl_Group>,
   HelpText<"OpenCL only. Allow denormals to be flushed to zero.">;
 def cl_fp32_correctly_rounded_divide_sqrt : Flag<["-"], "cl-fp32-correctly-rounded-divide-sqrt">, Group<opencl_Group>, Flags<[CC1Option]>,