[pull] main from llvm:main

bolt/include/bolt/Rewrite/RewriteInstance.h

@@ -139,6 +139,9 @@ class RewriteInstance {
   void handleRelocation(const object::SectionRef &RelocatedSection,
                         const RelocationRef &Rel);
 
+  /// Collect functions that are specified to be bumped.
+  void selectFunctionsToPrint();
+
   /// Mark functions that are not meant for processing as ignored.
   void selectFunctionsToProcess();
 

bolt/lib/Core/BinaryFunction.cpp

@@ -61,6 +61,8 @@ extern cl::OptionCategory BoltOptCategory;
 
 extern cl::opt<bool> EnableBAT;
 extern cl::opt<bool> Instrument;
+extern cl::list<std::string> PrintOnly;
+extern cl::opt<std::string> PrintOnlyFile;
 extern cl::opt<bool> StrictMode;
 extern cl::opt<bool> UpdateDebugSections;
 extern cl::opt<unsigned> Verbosity;
@@ -133,14 +135,6 @@ PrintDynoStatsOnly("print-dyno-stats-only",
   cl::Hidden,
   cl::cat(BoltCategory));
 
-static cl::list<std::string>
-PrintOnly("print-only",
-  cl::CommaSeparated,
-  cl::desc("list of functions to print"),
-  cl::value_desc("func1,func2,func3,..."),
-  cl::Hidden,
-  cl::cat(BoltCategory));
-
 cl::opt<bool>
     TimeBuild("time-build",
               cl::desc("print time spent constructing binary functions"),

bolt/lib/Rewrite/RewriteInstance.cpp

@@ -82,6 +82,8 @@ extern cl::opt<bool> Hugify;
 extern cl::opt<bool> Instrument;
 extern cl::opt<bool> KeepNops;
 extern cl::opt<bool> Lite;
+extern cl::list<std::string> PrintOnly;
+extern cl::opt<std::string> PrintOnlyFile;
 extern cl::list<std::string> ReorderData;
 extern cl::opt<bolt::ReorderFunctions::ReorderType> ReorderFunctions;
 extern cl::opt<bool> TerminalHLT;
@@ -730,6 +732,8 @@ Error RewriteInstance::run() {
              << "\n";
   BC->outs() << "BOLT-INFO: BOLT version: " << BoltRevision << "\n";
 
+  selectFunctionsToPrint();
+
   if (Error E = discoverStorage())
     return E;
   if (Error E = readSpecialSections())
@@ -3100,17 +3104,22 @@ static BinaryFunction *getInitFunctionIfStaticBinary(BinaryContext &BC) {
   return BC.getBinaryFunctionAtAddress(BD->getAddress());
 }
 
+static void populateFunctionNames(cl::opt<std::string> &FunctionNamesFile,
+                                  cl::list<std::string> &FunctionNames) {
+  if (FunctionNamesFile.empty())
+    return;
+  std::ifstream FuncsFile(FunctionNamesFile, std::ios::in);
+  std::string FuncName;
+  while (std::getline(FuncsFile, FuncName))
+    FunctionNames.push_back(FuncName);
+}
+
+void RewriteInstance::selectFunctionsToPrint() {
+  populateFunctionNames(opts::PrintOnlyFile, opts::PrintOnly);
+}
+
 void RewriteInstance::selectFunctionsToProcess() {
   // Extend the list of functions to process or skip from a file.
-  auto populateFunctionNames = [](cl::opt<std::string> &FunctionNamesFile,
-                                  cl::list<std::string> &FunctionNames) {
-    if (FunctionNamesFile.empty())
-      return;
-    std::ifstream FuncsFile(FunctionNamesFile, std::ios::in);
-    std::string FuncName;
-    while (std::getline(FuncsFile, FuncName))
-      FunctionNames.push_back(FuncName);
-  };
   populateFunctionNames(opts::FunctionNamesFile, opts::ForceFunctionNames);
   populateFunctionNames(opts::SkipFunctionNamesFile, opts::SkipFunctionNames);
   populateFunctionNames(opts::FunctionNamesFileNR, opts::ForceFunctionNamesNR);

bolt/lib/Utils/CommandLineOpts.cpp

@@ -245,6 +245,16 @@ cl::opt<bool> PrintCacheMetrics(
     cl::desc("calculate and print various metrics for instruction cache"),
     cl::cat(BoltOptCategory));
 
+cl::list<std::string> PrintOnly("print-only", cl::CommaSeparated,
+                                cl::desc("list of functions to print"),
+                                cl::value_desc("func1,func2,func3,..."),
+                                cl::Hidden, cl::cat(BoltCategory));
+
+cl::opt<std::string>
+    PrintOnlyFile("print-only-file",
+                  cl::desc("file with list of functions to print"), cl::Hidden,
+                  cl::cat(BoltCategory));
+
 cl::opt<bool> PrintSections("print-sections",
                             cl::desc("print all registered sections"),
                             cl::Hidden, cl::cat(BoltCategory));

bolt/test/print-only.test

@@ -0,0 +1,25 @@
+# Verify if `--print-only` and `--print-only-files` work fine.
+
+# REQUIRES: system-linux
+
+# RUN: %clang %cflags -x c %p/Inputs/bolt_icf.cpp -o %t -Wl,-q
+# RUN: llvm-bolt %t -o %t.bolt --icf=none --print-cfg \
+# RUN:     --print-only=foo.*,bar.*,main.* 2>&1 | FileCheck %s
+
+# RUN: echo "bar.*" > %t.pof
+# RUN: echo "main.*" >> %t.pof
+# RUN: llvm-bolt %t -o %t.bolt --icf=none --print-cfg \
+# RUN:     --print-only=foo.* --print-only-file=%t.pof \
+# RUN:     2>&1 | FileCheck %s
+
+# RUN: echo "foo.*" >> %t.pof
+# RUN: llvm-bolt %t -o %t.bolt --icf=none --print-cfg \
+# RUN:     --print-only-file=%t.pof 2>&1 | FileCheck %s
+
+# CHECK-NOT: Binary Function "fiz" after building cfg
+# CHECK-NOT: Binary Function "faz" after building cfg
+# CHECK-NOT: Binary Function "zip" after building cfg
+# CHECK-NOT: Binary Function "zap" after building cfg
+# CHECK: Binary Function "foo" after building cfg
+# CHECK: Binary Function "bar" after building cfg
+# CHECK: Binary Function "main" after building cfg

clang/docs/ReleaseNotes.rst

@@ -69,6 +69,8 @@ Potentially Breaking Changes
   call the member ``operator delete`` instead of the expected global
   delete operator. The old behavior is retained under ``-fclang-abi-compat=21``
   flag.
+- Clang warning suppressions file, ``--warning-suppression-mappings=``, now will
+  use the last matching entry instead of the longest one.
 - Trailing null statements in GNU statement expressions are no longer
   ignored by Clang; they now result in a void type. Clang previously
   matched GCC's behavior, which was recently clarified to be incorrect.

clang/docs/WarningSuppressionMappings.rst

@@ -63,7 +63,7 @@ Format
 Warning suppression mappings uses the same format as
 :doc:`SanitizerSpecialCaseList`.
 
-Sections describe which diagnostic group's behaviour to change, e.g.
+Sections describe which diagnostic group's behavior to change, e.g.
 ``[unused]``. When a diagnostic is matched by multiple sections, the latest
 section takes precedence.
 
@@ -76,7 +76,7 @@ Source files are matched against these globs either:
 - as paths relative to the current working directory
 - as absolute paths.
 
-When a source file matches multiple globs in a section, the longest one takes
+When a source file matches multiple globs in a section, the last one takes
 precedence.
 
 .. code-block:: bash

clang/include/clang/Basic/Diagnostic.h

@@ -971,7 +971,7 @@ class DiagnosticsEngine : public RefCountedBase<DiagnosticsEngine> {
   /// diagnostics in specific files.
   /// Mapping file is expected to be a special case list with sections denoting
   /// diagnostic groups and `src` entries for globs to suppress. `emit` category
-  /// can be used to disable suppression. Longest glob that matches a filepath
+  /// can be used to disable suppression. The last glob that matches a filepath
   /// takes precedence. For example:
   ///   [unused]
   ///   src:clang/*

clang/lib/Basic/Diagnostic.cpp

@@ -525,8 +525,7 @@ std::unique_ptr<WarningsSpecialCaseList>
 WarningsSpecialCaseList::create(const llvm::MemoryBuffer &Input,
                                 std::string &Err) {
   auto WarningSuppressionList = std::make_unique<WarningsSpecialCaseList>();
-  if (!WarningSuppressionList->createInternal(&Input, Err,
-                                              /*OrderBySize=*/true))
+  if (!WarningSuppressionList->createInternal(&Input, Err))
     return nullptr;
   return WarningSuppressionList;
 }
@@ -588,15 +587,12 @@ bool WarningsSpecialCaseList::isDiagSuppressed(diag::kind DiagId,
 
   StringRef F = llvm::sys::path::remove_leading_dotslash(PLoc.getFilename());
 
-  StringRef LongestSup = DiagSection->getLongestMatch("src", F, "");
-  if (LongestSup.empty())
+  unsigned LastSup = DiagSection->getLastMatch("src", F, "");
+  if (LastSup == 0)
     return false;
 
-  StringRef LongestEmit = DiagSection->getLongestMatch("src", F, "emit");
-  if (LongestEmit.empty())
-    return true;
-
-  return LongestSup.size() > LongestEmit.size();
+  unsigned LastEmit = DiagSection->getLastMatch("src", F, "emit");
+  return LastSup > LastEmit;
 }
 
 bool DiagnosticsEngine::isSuppressedViaMapping(diag::kind DiagId,

clang/lib/CIR/CodeGen/CIRGenBuilder.h

@@ -315,8 +315,10 @@ class CIRGenBuilderTy : public cir::CIRBaseBuilderTy {
     return getConstantInt(loc, getUInt32Ty(), c);
   }
   cir::ConstantOp getSInt64(uint64_t c, mlir::Location loc) {
-    cir::IntType sInt64Ty = getSInt64Ty();
-    return cir::ConstantOp::create(*this, loc, cir::IntAttr::get(sInt64Ty, c));
+    return getConstantInt(loc, getSInt64Ty(), c);
+  }
+  cir::ConstantOp getUInt64(uint64_t c, mlir::Location loc) {
+    return getConstantInt(loc, getUInt64Ty(), c);
   }
 
   mlir::Value createNeg(mlir::Value value) {

clang/lib/CIR/CodeGen/CIRGenBuiltin.cpp

@@ -630,6 +630,22 @@ CIRGenFunction::emitTargetBuiltinExpr(unsigned builtinID, const CallExpr *e,
                                    getTarget().getTriple().getArch());
 }
 
+mlir::Value CIRGenFunction::emitScalarOrConstFoldImmArg(
+    const unsigned iceArguments, const unsigned idx, const Expr *argExpr) {
+  mlir::Value arg = {};
+  if ((iceArguments & (1 << idx)) == 0) {
+    arg = emitScalarExpr(argExpr);
+  } else {
+    // If this is required to be a constant, constant fold it so that we
+    // know that the generated intrinsic gets a ConstantInt.
+    const std::optional<llvm::APSInt> result =
+        argExpr->getIntegerConstantExpr(getContext());
+    assert(result && "Expected argument to be a constant");
+    arg = builder.getConstInt(getLoc(argExpr->getSourceRange()), *result);
+  }
+  return arg;
+}
+
 /// Given a builtin id for a function like "__builtin_fabsf", return a Function*
 /// for "fabsf".
 cir::FuncOp CIRGenModule::getBuiltinLibFunction(const FunctionDecl *fd,

clang/lib/CIR/CodeGen/CIRGenBuiltinX86.cpp

@@ -16,7 +16,6 @@
 #include "clang/Basic/Builtins.h"
 #include "clang/Basic/TargetBuiltins.h"
 #include "clang/CIR/MissingFeatures.h"
-#include "llvm/IR/IntrinsicsX86.h"
 
 using namespace clang;
 using namespace clang::CIRGen;
@@ -66,9 +65,8 @@ mlir::Value CIRGenFunction::emitX86BuiltinExpr(unsigned builtinID,
   getContext().GetBuiltinType(builtinID, error, &iceArguments);
   assert(error == ASTContext::GE_None && "Error while getting builtin type.");
 
-  for (auto [idx, arg] : llvm::enumerate(e->arguments())) {
+  for (auto [idx, arg] : llvm::enumerate(e->arguments()))
     ops.push_back(emitScalarOrConstFoldImmArg(iceArguments, idx, arg));
-  }
 
   CIRGenBuilderTy &builder = getBuilder();
   mlir::Type voidTy = builder.getVoidTy();
@@ -98,6 +96,10 @@ mlir::Value CIRGenFunction::emitX86BuiltinExpr(unsigned builtinID,
   case X86::BI__builtin_ia32_undef128:
   case X86::BI__builtin_ia32_undef256:
   case X86::BI__builtin_ia32_undef512:
+    cgm.errorNYI(e->getSourceRange(),
+                 std::string("unimplemented X86 builtin call: ") +
+                     getContext().BuiltinInfo.getName(builtinID));
+    return {};
   case X86::BI__builtin_ia32_vec_ext_v4hi:
   case X86::BI__builtin_ia32_vec_ext_v16qi:
   case X86::BI__builtin_ia32_vec_ext_v8hi:
@@ -107,7 +109,22 @@ mlir::Value CIRGenFunction::emitX86BuiltinExpr(unsigned builtinID,
   case X86::BI__builtin_ia32_vec_ext_v32qi:
   case X86::BI__builtin_ia32_vec_ext_v16hi:
   case X86::BI__builtin_ia32_vec_ext_v8si:
-  case X86::BI__builtin_ia32_vec_ext_v4di:
+  case X86::BI__builtin_ia32_vec_ext_v4di: {
+    unsigned numElts = cast<cir::VectorType>(ops[0].getType()).getSize();
+
+    uint64_t index =
+        ops[1].getDefiningOp<cir::ConstantOp>().getIntValue().getZExtValue();
+
+    index &= numElts - 1;
+
+    cir::ConstantOp indexVal =
+        builder.getUInt64(index, getLoc(e->getExprLoc()));
+
+    // These builtins exist so we can ensure the index is an ICE and in range.
+    // Otherwise we could just do this in the header file.
+    return cir::VecExtractOp::create(builder, getLoc(e->getExprLoc()), ops[0],
+                                     indexVal);
+  }
   case X86::BI__builtin_ia32_vec_set_v4hi:
   case X86::BI__builtin_ia32_vec_set_v16qi:
   case X86::BI__builtin_ia32_vec_set_v8hi:

clang/lib/CIR/CodeGen/CIRGenExprScalar.cpp

@@ -1442,28 +1442,6 @@ mlir::Value CIRGenFunction::emitPromotedScalarExpr(const Expr *e,
   return ScalarExprEmitter(*this, builder).Visit(const_cast<Expr *>(e));
 }
 
-mlir::Value CIRGenFunction::emitScalarOrConstFoldImmArg(unsigned iceArguments,
-                                                        unsigned index,
-                                                        const Expr *arg) {
-  mlir::Value result{};
-
-  // The bit at the specified index indicates whether the argument is required
-  // to be a constant integer expression.
-  bool isArgRequiredToBeConstant = (iceArguments & (1 << index));
-
-  if (!isArgRequiredToBeConstant) {
-    result = emitScalarExpr(arg);
-  } else {
-    // If this is required to be a constant, constant fold it so that we
-    // know that the generated intrinsic gets a ConstantInt.
-    std::optional<llvm::APSInt> iceOpt =
-        arg->getIntegerConstantExpr(getContext());
-    assert(iceOpt && "Expected argument to be a constant");
-    result = builder.getConstInt(getLoc(arg->getSourceRange()), *iceOpt);
-  }
-  return result;
-}
-
 [[maybe_unused]] static bool mustVisitNullValue(const Expr *e) {
   // If a null pointer expression's type is the C++0x nullptr_t and
   // the expression is not a simple literal, it must be evaluated

clang/lib/CIR/CodeGen/CIRGenFunction.h

@@ -1546,9 +1546,6 @@ class CIRGenFunction : public CIRGenTypeCache {
   mlir::Value emitScalarExpr(const clang::Expr *e,
                              bool ignoreResultAssign = false);
 
-  mlir::Value emitScalarOrConstFoldImmArg(unsigned iceArguments, unsigned index,
-                                          const Expr *arg);
-
   mlir::Value emitScalarPrePostIncDec(const UnaryOperator *e, LValue lv,
                                       cir::UnaryOpKind kind, bool isPre);
 
@@ -1721,6 +1718,9 @@ class CIRGenFunction : public CIRGenTypeCache {
   void emitScalarInit(const clang::Expr *init, mlir::Location loc,
                       LValue lvalue, bool capturedByInit = false);
 
+  mlir::Value emitScalarOrConstFoldImmArg(unsigned iceArguments, unsigned idx,
+                                          const Expr *argExpr);
+
   void emitStaticVarDecl(const VarDecl &d, cir::GlobalLinkageKind linkage);
 
   void emitStoreOfComplex(mlir::Location loc, mlir::Value v, LValue dest,

clang/lib/CodeGen/BackendUtil.cpp

@@ -481,6 +481,36 @@ static bool initTargetOptions(const CompilerInstance &CI,
   Options.JMCInstrument = CodeGenOpts.JMCInstrument;
   Options.XCOFFReadOnlyPointers = CodeGenOpts.XCOFFReadOnlyPointers;
 
+  switch (CodeGenOpts.getVecLib()) {
+  case llvm::driver::VectorLibrary::NoLibrary:
+    Options.VecLib = llvm::VectorLibrary::NoLibrary;
+    break;
+  case llvm::driver::VectorLibrary::Accelerate:
+    Options.VecLib = llvm::VectorLibrary::Accelerate;
+    break;
+  case llvm::driver::VectorLibrary::Darwin_libsystem_m:
+    Options.VecLib = llvm::VectorLibrary::DarwinLibSystemM;
+    break;
+  case llvm::driver::VectorLibrary::LIBMVEC:
+    Options.VecLib = llvm::VectorLibrary::LIBMVEC;
+    break;
+  case llvm::driver::VectorLibrary::MASSV:
+    Options.VecLib = llvm::VectorLibrary::MASSV;
+    break;
+  case llvm::driver::VectorLibrary::SVML:
+    Options.VecLib = llvm::VectorLibrary::SVML;
+    break;
+  case llvm::driver::VectorLibrary::SLEEF:
+    Options.VecLib = llvm::VectorLibrary::SLEEFGNUABI;
+    break;
+  case llvm::driver::VectorLibrary::ArmPL:
+    Options.VecLib = llvm::VectorLibrary::ArmPL;
+    break;
+  case llvm::driver::VectorLibrary::AMDLIBM:
+    Options.VecLib = llvm::VectorLibrary::AMDLIBM;
+    break;
+  }
+
   switch (CodeGenOpts.getSwiftAsyncFramePointer()) {
   case CodeGenOptions::SwiftAsyncFramePointerKind::Auto:
     Options.SwiftAsyncFramePointer =
@@ -584,6 +614,7 @@ static void setCommandLineOpts(const CodeGenOptions &CodeGenOpts,
     BackendArgs.push_back("-limit-float-precision");
     BackendArgs.push_back(CodeGenOpts.LimitFloatPrecision.c_str());
   }
+
   // Check for the default "clang" invocation that won't set any cl::opt values.
   // Skip trying to parse the command line invocation to avoid the issues
   // described below.

clang/lib/Sema/SemaOpenMP.cpp

@@ -1364,15 +1364,15 @@ DSAStackTy::DSAVarData DSAStackTy::getDSA(const_iterator &Iter,
   DefaultDataSharingAttributes IterDA = Iter->DefaultAttr;
   switch (Iter->DefaultVCAttr) {
   case DSA_VC_aggregate:
-    if (!D->getType()->isAggregateType())
+    if (!VD->getType()->isAggregateType())
       IterDA = DSA_none;
     break;
   case DSA_VC_pointer:
-    if (!D->getType()->isPointerType())
+    if (!VD->getType()->isPointerType())
       IterDA = DSA_none;
     break;
   case DSA_VC_scalar:
-    if (!D->getType()->isScalarType())
+    if (!VD->getType()->isScalarType())
       IterDA = DSA_none;
     break;
   case DSA_VC_all: