Common infrastructure for reading a profile remapping file and building

a mangling remapper from it.

Differential Revision: https://reviews.llvm.org/D51246

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@342161 91177308-0d34-0410-b5e6-96231b3b80d8

include/llvm/Support/SymbolRemappingReader.h

@@ -0,0 +1,133 @@
+//===- SymbolRemappingReader.h - Read symbol remapping file -----*- C++ -*-===//
+//
+//                      The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file contains definitions needed for reading and applying symbol
+// remapping files.
+//
+// Support is provided only for the Itanium C++ name mangling scheme for now.
+//
+// NOTE: If you are making changes to this file format, please remember
+//       to document them in the Clang documentation at
+//       tools/clang/docs/UsersManual.rst.
+//
+// File format
+// -----------
+//
+// The symbol remappings are written as an ASCII text file. Blank lines and
+// lines starting with a # are ignored. All other lines specify a kind of
+// mangled name fragment, along with two fragments of that kind that should
+// be treated as equivalent, separated by spaces.
+//
+// See http://itanium-cxx-abi.github.io/cxx-abi/abi.html#mangling for a
+// description of the Itanium name mangling scheme.
+//
+// The accepted fragment kinds are:
+//
+//  * name  A <name>, such as 6foobar or St3__1
+//  * type  A <type>, such as Ss or N4llvm9StringRefE
+//  * encoding  An <encoding> (a complete mangling without the leading _Z)
+//
+// For example:
+//
+// # Ignore int / long differences to treat symbols from 32-bit and 64-bit
+// # builds with differing size_t / ptrdiff_t / intptr_t as equivalent.
+// type i l
+// type j m
+//
+// # Ignore differences between libc++ and libstdc++, and between libstdc++'s
+// # C++98 and C++11 ABIs.
+// name 3std St3__1
+// name 3std St7__cxx11
+//
+// # Remap a function overload to a specialization of a template (including
+// # any local symbols declared within it).
+// encoding N2NS1fEi N2NS1fIiEEvT_
+//
+// # Substitutions must be remapped separately from namespace 'std' for now.
+// name Sa NSt3__19allocatorE
+// name Sb NSt3__112basic_stringE
+// type Ss NSt3__112basic_stringIcSt11char_traitsIcESaE
+// # ...
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_SUPPORT_SYMBOLREMAPPINGREADER_H
+#define LLVM_SUPPORT_SYMBOLREMAPPINGREADER_H
+
+#include "llvm/ADT/StringRef.h"
+#include "llvm/Support/Error.h"
+#include "llvm/Support/ItaniumManglingCanonicalizer.h"
+#include "llvm/Support/MemoryBuffer.h"
+
+namespace llvm {
+
+class SymbolRemappingParseError : public ErrorInfo<SymbolRemappingParseError> {
+public:
+  SymbolRemappingParseError(StringRef File, int64_t Line, Twine Message)
+      : File(File), Line(Line), Message(Message.str()) {}
+
+  void log(llvm::raw_ostream &OS) const override {
+    OS << File << ':' << Line << ": " << Message;
+  }
+  std::error_code convertToErrorCode() const override {
+    return llvm::inconvertibleErrorCode();
+  }
+
+  StringRef getFileName() const { return File; }
+  int64_t getLineNum() const { return Line; }
+  StringRef getMessage() const { return Message; }
+
+  static char ID;
+
+private:
+  std::string File;
+  int64_t Line;
+  std::string Message;
+};
+
+/// Reader for symbol remapping files.
+///
+/// Remaps the symbol names in profile data to match those in the program
+/// according to a set of rules specified in a given file.
+class SymbolRemappingReader {
+public:
+  /// Read remappings from the given buffer, which must live as long as
+  /// the remapper.
+  Error read(MemoryBuffer &B);
+
+  /// A Key represents an equivalence class of symbol names.
+  using Key = uintptr_t;
+
+  /// Construct a key for the given symbol, or return an existing one if an
+  /// equivalent name has already been inserted. The symbol name must live
+  /// as long as the remapper.
+  ///
+  /// The result will be Key() if the name cannot be remapped (typically
+  /// because it is not a valid mangled name).
+  Key insert(StringRef FunctionName) {
+    return Canonicalizer.canonicalize(FunctionName);
+  }
+
+  /// Map the given symbol name into the key for the corresponding equivalence
+  /// class.
+  ///
+  /// The result will typically be Key() if no equivalent symbol has been
+  /// inserted, but this is not guaranteed: a Key different from all keys ever
+  /// returned by \c insert may be returned instead.
+  Key lookup(StringRef FunctionName) {
+    return Canonicalizer.lookup(FunctionName);
+  }
+
+private:
+  ItaniumManglingCanonicalizer Canonicalizer;
+};
+
+} // end namespace llvm
+
+#endif // LLVM_SUPPORT_SYMBOLREMAPPINGREADER_H

lib/Support/CMakeLists.txt

@@ -122,6 +122,7 @@ add_llvm_library(LLVMSupport
   StringPool.cpp
   StringSaver.cpp
   StringRef.cpp
+  SymbolRemappingReader.cpp
   SystemUtils.cpp
   TarWriter.cpp
   TargetParser.cpp

lib/Support/SymbolRemappingReader.cpp

@@ -0,0 +1,81 @@
+//===- SymbolRemappingReader.cpp - Read symbol remapping file -------------===//
+//
+//                      The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file contains definitions needed for reading and applying symbol
+// remapping files.
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/Support/SymbolRemappingReader.h"
+#include "llvm/ADT/StringSwitch.h"
+#include "llvm/ADT/Twine.h"
+#include "llvm/Support/LineIterator.h"
+
+using namespace llvm;
+
+char SymbolRemappingParseError::ID;
+
+/// Load a set of name remappings from a text file.
+///
+/// See the documentation at the top of the file for an explanation of
+/// the expected format.
+Error SymbolRemappingReader::read(MemoryBuffer &B) {
+  line_iterator LineIt(B, /*SkipBlanks=*/true, '#');
+
+  auto ReportError = [&](Twine Msg) {
+    return llvm::make_error<SymbolRemappingParseError>(
+        B.getBufferIdentifier(), LineIt.line_number(), Msg);
+  };
+
+  for (; !LineIt.is_at_eof(); ++LineIt) {
+    StringRef Line = *LineIt;
+    Line = Line.ltrim(' ');
+    // line_iterator only detects comments starting in column 1.
+    if (Line.startswith("#") || Line.empty())
+      continue;
+
+    SmallVector<StringRef, 4> Parts;
+    Line.split(Parts, ' ', /*MaxSplits*/-1, /*KeepEmpty*/false);
+
+    if (Parts.size() != 3)
+      return ReportError("Expected 'kind mangled_name mangled_name', "
+                         "found '" + Line + "'");
+
+    using FK = ItaniumManglingCanonicalizer::FragmentKind;
+    Optional<FK> FragmentKind = StringSwitch<Optional<FK>>(Parts[0])
+                                    .Case("name", FK::Name)
+                                    .Case("type", FK::Type)
+                                    .Case("encoding", FK::Encoding)
+                                    .Default(None);
+    if (!FragmentKind)
+      return ReportError("Invalid kind, expected 'name', 'type', or 'encoding',"
+                         " found '" + Parts[0] + "'");
+
+    using EE = ItaniumManglingCanonicalizer::EquivalenceError;
+    switch (Canonicalizer.addEquivalence(*FragmentKind, Parts[1], Parts[2])) {
+    case EE::Success:
+      break;
+
+    case EE::ManglingAlreadyUsed:
+      return ReportError("Manglings '" + Parts[1] + "' and '" + Parts[2] + "' "
+                         "have both been used in prior remappings. Move this "
+                         "remapping earlier in the file.");
+
+    case EE::InvalidFirstMangling:
+      return ReportError("Could not demangle '" + Parts[1] + "' "
+                         "as a <" + Parts[0] + ">; invalid mangling?");
+
+    case EE::InvalidSecondMangling:
+      return ReportError("Could not demangle '" + Parts[2] + "' "
+                         "as a <" + Parts[0] + ">; invalid mangling?");
+    }
+  }
+
+  return Error::success();
+}

unittests/Support/CMakeLists.txt

@@ -54,6 +54,7 @@ add_llvm_unittest(SupportTests
   SpecialCaseListTest.cpp
   StringPool.cpp
   SwapByteOrderTest.cpp
+  SymbolRemappingReaderTest.cpp
   TarWriterTest.cpp
   TargetParserTest.cpp
   TaskQueueTest.cpp

unittests/Support/SymbolRemappingReaderTest.cpp

@@ -0,0 +1,96 @@
+//===- unittests/Support/SymbolRemappingReaderTest.cpp --------------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/Support/SymbolRemappingReader.h"
+#include "llvm/Support/MemoryBuffer.h"
+#include "gtest/gtest.h"
+
+using namespace llvm;
+
+namespace {
+class SymbolRemappingReaderTest : public testing::Test {
+public:
+  std::unique_ptr<MemoryBuffer> Buffer;
+  SymbolRemappingReader Reader;
+
+  std::string readWithErrors(StringRef Text, StringRef BufferName) {
+    Buffer = MemoryBuffer::getMemBuffer(Text, BufferName);
+    Error E = Reader.read(*Buffer);
+    EXPECT_TRUE((bool)E);
+    return toString(std::move(E));
+  }
+
+  void read(StringRef Text, StringRef BufferName) {
+    Buffer = MemoryBuffer::getMemBuffer(Text, BufferName);
+    Error E = Reader.read(*Buffer);
+    EXPECT_FALSE((bool)E);
+  }
+};
+} // unnamed namespace
+
+TEST_F(SymbolRemappingReaderTest, ParseErrors) {
+  EXPECT_EQ(readWithErrors("error", "foo.map"),
+            "foo.map:1: Expected 'kind mangled_name mangled_name', "
+            "found 'error'");
+
+  EXPECT_EQ(readWithErrors("error m1 m2", "foo.map"),
+            "foo.map:1: Invalid kind, expected 'name', 'type', or 'encoding', "
+            "found 'error'");
+}
+
+TEST_F(SymbolRemappingReaderTest, DemanglingErrors) {
+  EXPECT_EQ(readWithErrors("type i banana", "foo.map"),
+            "foo.map:1: Could not demangle 'banana' as a <type>; "
+            "invalid mangling?");
+  EXPECT_EQ(readWithErrors("name i 1X", "foo.map"),
+            "foo.map:1: Could not demangle 'i' as a <name>; "
+            "invalid mangling?");
+  EXPECT_EQ(readWithErrors("name 1X 1fv", "foo.map"),
+            "foo.map:1: Could not demangle '1fv' as a <name>; "
+            "invalid mangling?");
+  EXPECT_EQ(readWithErrors("encoding 1fv 1f1gE", "foo.map"),
+            "foo.map:1: Could not demangle '1f1gE' as a <encoding>; "
+            "invalid mangling?");
+}
+
+TEST_F(SymbolRemappingReaderTest, BadMappingOrder) {
+  StringRef Map = R"(
+    # N::foo == M::bar
+    name N1N3fooE N1M3barE
+
+    # N:: == M::
+    name 1N 1M
+  )";
+  EXPECT_EQ(readWithErrors(Map, "foo.map"),
+            "foo.map:6: Manglings '1N' and '1M' have both been used in prior "
+            "remappings. Move this remapping earlier in the file.");
+}
+
+TEST_F(SymbolRemappingReaderTest, RemappingsAdded) {
+  StringRef Map = R"(
+    # A::foo == B::bar
+    name N1A3fooE N1B3barE
+
+    # int == long
+    type i l
+
+    # void f<int>() = void g<int>()
+    encoding 1fIiEvv 1gIiEvv
+  )";
+
+  read(Map, "foo.map");
+  auto Key = Reader.insert("_ZN1B3bar3bazIiEEvv");
+  EXPECT_NE(Key, SymbolRemappingReader::Key());
+  EXPECT_EQ(Key, Reader.lookup("_ZN1A3foo3bazIlEEvv"));
+  EXPECT_NE(Key, Reader.lookup("_ZN1C3foo3bazIlEEvv"));
+
+  Key = Reader.insert("_Z1fIiEvv");
+  EXPECT_NE(Key, SymbolRemappingReader::Key());
+  EXPECT_EQ(Key, Reader.lookup("_Z1gIlEvv"));
+}