[XRay] Define the library for XRay trace logs

Summary:
In this change we move the definition of the log reading routines from
the tools directory in LLVM to {include/llvm,lib}/XRay. We improve the
documentation a little bit for the publicly accessible headers, and
adjust the top-matter. This also leads to some refactoring and cleanup
in the tooling code.

In particular, we do the following:

  - Rename the class from LogReader to Trace, as it better represents
    the logical set of records as opposed to a log.
  - Use file type detection instead of asking the user to say what
    format the input file is. This allows us to keep the interface
    simple and encapsulate the logic of loading the data appropriately.

In future changes we increase the API surface and write dedicated unit
tests for the XRay library.

Depends on D24376.

Reviewers: dblaikie, echristo

Subscribers: mehdi_amini, mgorny, llvm-commits, varno

Differential Revision: https://reviews.llvm.org/D28345

llvm-svn: 291652

7 files changed, 26 insertions, 422 deletions

diff --git a/llvm/tools/llvm-xray/CMakeLists.txt b/llvm/tools/llvm-xray/CMakeLists.txt
index 5b0b854cb29..e8cfe9f709e 100644
--- a/llvm/tools/llvm-xray/CMakeLists.txt
+++ b/llvm/tools/llvm-xray/CMakeLists.txt
@@ -3,14 +3,14 @@ set(LLVM_LINK_COMPONENTS
   DebugInfoDWARF
   Object
   Support
-  Symbolize)
+  Symbolize
+  XRay)
 
 set(LLVM_XRAY_TOOLS
   func-id-helper.cc
   xray-converter.cc
   xray-extract.cc
   xray-extract.cc
-  xray-log-reader.cc
   xray-registry.cc)
 
 add_llvm_tool(llvm-xray llvm-xray.cc ${LLVM_XRAY_TOOLS})
diff --git a/llvm/tools/llvm-xray/xray-converter.cc b/llvm/tools/llvm-xray/xray-converter.cc
index 81fdca2d26c..7dfc8374c28 100644
--- a/llvm/tools/llvm-xray/xray-converter.cc
+++ b/llvm/tools/llvm-xray/xray-converter.cc
@@ -13,13 +13,14 @@
 #include "xray-converter.h"
 
 #include "xray-extract.h"
-#include "xray-record-yaml.h"
 #include "xray-registry.h"
 #include "llvm/DebugInfo/Symbolize/Symbolize.h"
 #include "llvm/Support/EndianStream.h"
 #include "llvm/Support/FileSystem.h"
 #include "llvm/Support/YAMLTraits.h"
 #include "llvm/Support/raw_ostream.h"
+#include "llvm/XRay/Trace.h"
+#include "llvm/XRay/YAMLXRayRecord.h"
 
 using namespace llvm;
 using namespace xray;
@@ -31,15 +32,6 @@ static cl::opt<std::string> ConvertInput(cl::Positional,
                                          cl::desc("<xray log file>"),
                                          cl::Required, cl::sub(Convert));
 enum class ConvertFormats { BINARY, YAML };
-static cl::opt<ConvertFormats> ConvertInputFormat(
-    "input-format", cl::desc("input format"),
-    cl::values(clEnumValN(ConvertFormats::BINARY, "raw",
-                          "input is in raw binary"),
-               clEnumValN(ConvertFormats::YAML, "yaml", "input is in yaml")),
-    cl::sub(Convert));
-static cl::alias ConvertInputFormat2("i", cl::aliasopt(ConvertInputFormat),
-                                     cl::desc("Alias for -input-format"),
-                                     cl::sub(Convert));
 static cl::opt<ConvertFormats> ConvertOutputFormat(
     "output-format", cl::desc("output format"),
     cl::values(clEnumValN(ConvertFormats::BINARY, "raw", "output in binary"),
@@ -91,12 +83,10 @@ static cl::alias InstrMapFormat2("t", cl::aliasopt(InstrMapFormat),
                                  cl::desc("Alias for -instr-map-format"),
                                  cl::sub(Convert));
 
-using llvm::yaml::MappingTraits;
-using llvm::yaml::ScalarEnumerationTraits;
 using llvm::yaml::IO;
 using llvm::yaml::Output;
 
-void TraceConverter::exportAsYAML(const LogReader &Records, raw_ostream &OS) {
+void TraceConverter::exportAsYAML(const Trace &Records, raw_ostream &OS) {
   YAMLXRayTrace Trace;
   const auto &FH = Records.getFileHeader();
   Trace.Header = {FH.Version, FH.Type, FH.ConstantTSC, FH.NonstopTSC,
@@ -112,7 +102,7 @@ void TraceConverter::exportAsYAML(const LogReader &Records, raw_ostream &OS) {
   Out << Trace;
 }
 
-void TraceConverter::exportAsRAWv1(const LogReader &Records, raw_ostream &OS) {
+void TraceConverter::exportAsRAWv1(const Trace &Records, raw_ostream &OS) {
   // First write out the file header, in the correct endian-appropriate format
   // (XRay assumes currently little endian).
   support::endian::Writer<support::endianness::little> Writer(OS);
@@ -180,24 +170,6 @@ static CommandRegistration Unused(&Convert, []() -> Error {
   llvm::xray::FuncIdConversionHelper FuncIdHelper(ConvertInstrMap, Symbolizer,
                                                   FunctionAddresses);
   llvm::xray::TraceConverter TC(FuncIdHelper, ConvertSymbolize);
-  LogReader::LoaderFunction Loader;
-  switch (ConvertInputFormat) {
-  case ConvertFormats::BINARY:
-    Loader = NaiveLogLoader;
-    break;
-  case ConvertFormats::YAML:
-    Loader = YAMLLogLoader;
-    break;
-  }
-
-  LogReader Reader(ConvertInput, Err, ConvertSortInput, Loader);
-  if (Err)
-    return joinErrors(
-        make_error<StringError>(
-            Twine("Failed loading input file '") + ConvertInput + "'.",
-            std::make_error_code(std::errc::executable_format_error)),
-        std::move(Err));
-
   raw_fd_ostream OS(ConvertOutput, EC,
                     ConvertOutputFormat == ConvertFormats::BINARY
                         ? sys::fs::OpenFlags::F_None
@@ -206,13 +178,22 @@ static CommandRegistration Unused(&Convert, []() -> Error {
     return make_error<StringError>(
         Twine("Cannot open file '") + ConvertOutput + "' for writing.", EC);
 
-  switch (ConvertOutputFormat) {
-  case ConvertFormats::YAML:
-    TC.exportAsYAML(Reader, OS);
-    break;
-  case ConvertFormats::BINARY:
-    TC.exportAsRAWv1(Reader, OS);
-    break;
+  if (auto TraceOrErr = loadTraceFile(ConvertInput, ConvertSortInput)) {
+    auto &T = *TraceOrErr;
+    switch (ConvertOutputFormat) {
+    case ConvertFormats::YAML:
+      TC.exportAsYAML(T, OS);
+      break;
+    case ConvertFormats::BINARY:
+      TC.exportAsRAWv1(T, OS);
+      break;
+    }
+  } else {
+    return joinErrors(
+        make_error<StringError>(
+            Twine("Failed loading input file '") + ConvertInput + "'.",
+            std::make_error_code(std::errc::protocol_error)),
+        TraceOrErr.takeError());
   }
   return Error::success();
 });
diff --git a/llvm/tools/llvm-xray/xray-converter.h b/llvm/tools/llvm-xray/xray-converter.h
index f830c7fa316..fa0d5e132f1 100644
--- a/llvm/tools/llvm-xray/xray-converter.h
+++ b/llvm/tools/llvm-xray/xray-converter.h
@@ -15,8 +15,8 @@
 #define LLVM_TOOLS_LLVM_XRAY_XRAY_CONVERTER_H
 
 #include "func-id-helper.h"
-#include "xray-log-reader.h"
-#include "xray-record.h"
+#include "llvm/XRay/XRayRecord.h"
+#include "llvm/XRay/Trace.h"
 
 namespace llvm {
 namespace xray {
@@ -29,8 +29,8 @@ public:
   TraceConverter(FuncIdConversionHelper &FuncIdHelper, bool Symbolize = false)
       : FuncIdHelper(FuncIdHelper), Symbolize(Symbolize) {}
 
-  void exportAsYAML(const LogReader &Records, raw_ostream &OS);
-  void exportAsRAWv1(const LogReader &Records, raw_ostream &OS);
+  void exportAsYAML(const Trace &Records, raw_ostream &OS);
+  void exportAsRAWv1(const Trace &Records, raw_ostream &OS);
 };
 
 } // namespace xray
diff --git a/llvm/tools/llvm-xray/xray-log-reader.cc b/llvm/tools/llvm-xray/xray-log-reader.cc
deleted file mode 100644
index 1dc745fe59a..00000000000
--- a/llvm/tools/llvm-xray/xray-log-reader.cc
+++ /dev/null
@@ -1,163 +0,0 @@
-//===- xray-log-reader.cc - XRay Log Reader Implementation ----------------===//
-//
-//                     The LLVM Compiler Infrastructure
-//
-// This file is distributed under the University of Illinois Open Source
-// License. See LICENSE.TXT for details.
-//
-//===----------------------------------------------------------------------===//
-//
-// XRay log reader implementation.
-//
-//===----------------------------------------------------------------------===//
-#include "xray-log-reader.h"
-#include "xray-record-yaml.h"
-#include "llvm/Support/DataExtractor.h"
-#include "llvm/Support/FileSystem.h"
-
-using namespace llvm;
-using namespace llvm::xray;
-using llvm::yaml::Input;
-
-LogReader::LogReader(
-    StringRef Filename, Error &Err, bool Sort,
-    std::function<Error(StringRef, XRayFileHeader &, std::vector<XRayRecord> &)>
-        Loader) {
-  ErrorAsOutParameter Guard(&Err);
-  int Fd;
-  if (auto EC = sys::fs::openFileForRead(Filename, Fd)) {
-    Err = make_error<StringError>(
-        Twine("Cannot read log from '") + Filename + "'", EC);
-    return;
-  }
-  uint64_t FileSize;
-  if (auto EC = sys::fs::file_size(Filename, FileSize)) {
-    Err = make_error<StringError>(
-        Twine("Cannot read log from '") + Filename + "'", EC);
-    return;
-  }
-
-  std::error_code EC;
-  sys::fs::mapped_file_region MappedFile(
-      Fd, sys::fs::mapped_file_region::mapmode::readonly, FileSize, 0, EC);
-  if (EC) {
-    Err = make_error<StringError>(
-        Twine("Cannot read log from '") + Filename + "'", EC);
-    return;
-  }
-
-  if (auto E = Loader(StringRef(MappedFile.data(), MappedFile.size()),
-                      FileHeader, Records)) {
-    Err = std::move(E);
-    return;
-  }
-
-  if (Sort)
-    std::sort(
-        Records.begin(), Records.end(),
-        [](const XRayRecord &L, const XRayRecord &R) { return L.TSC < R.TSC; });
-}
-
-Error llvm::xray::NaiveLogLoader(StringRef Data, XRayFileHeader &FileHeader,
-                                 std::vector<XRayRecord> &Records) {
-  // FIXME: Maybe deduce whether the data is little or big-endian using some
-  // magic bytes in the beginning of the file?
-
-  // First 32 bytes of the file will always be the header. We assume a certain
-  // format here:
-  //
-  //   (2)   uint16 : version
-  //   (2)   uint16 : type
-  //   (4)   uint32 : bitfield
-  //   (8)   uint64 : cycle frequency
-  //   (16)  -      : padding
-  //
-  if (Data.size() < 32)
-    return make_error<StringError>(
-        "Not enough bytes for an XRay log.",
-        std::make_error_code(std::errc::invalid_argument));
-
-  if (Data.size() - 32 == 0 || Data.size() % 32 != 0)
-    return make_error<StringError>(
-        "Invalid-sized XRay data.",
-        std::make_error_code(std::errc::invalid_argument));
-
-  DataExtractor HeaderExtractor(Data, true, 8);
-  uint32_t OffsetPtr = 0;
-  FileHeader.Version = HeaderExtractor.getU16(&OffsetPtr);
-  FileHeader.Type = HeaderExtractor.getU16(&OffsetPtr);
-  uint32_t Bitfield = HeaderExtractor.getU32(&OffsetPtr);
-  FileHeader.ConstantTSC = Bitfield & 1uL;
-  FileHeader.NonstopTSC = Bitfield & 1uL << 1;
-  FileHeader.CycleFrequency = HeaderExtractor.getU64(&OffsetPtr);
-
-  if (FileHeader.Version != 1)
-    return make_error<StringError>(
-        Twine("Unsupported XRay file version: ") + Twine(FileHeader.Version),
-        std::make_error_code(std::errc::invalid_argument));
-
-  // Each record after the header will be 32 bytes, in the following format:
-  //
-  //   (2)   uint16 : record type
-  //   (1)   uint8  : cpu id
-  //   (1)   uint8  : type
-  //   (4)   sint32 : function id
-  //   (8)   uint64 : tsc
-  //   (4)   uint32 : thread id
-  //   (12)  -      : padding
-  for (auto S = Data.drop_front(32); !S.empty(); S = S.drop_front(32)) {
-    DataExtractor RecordExtractor(S, true, 8);
-    uint32_t OffsetPtr = 0;
-    Records.emplace_back();
-    auto &Record = Records.back();
-    Record.RecordType = RecordExtractor.getU16(&OffsetPtr);
-    Record.CPU = RecordExtractor.getU8(&OffsetPtr);
-    auto Type = RecordExtractor.getU8(&OffsetPtr);
-    switch (Type) {
-    case 0:
-      Record.Type = RecordTypes::ENTER;
-      break;
-    case 1:
-      Record.Type = RecordTypes::EXIT;
-      break;
-    default:
-      return make_error<StringError>(
-          Twine("Unknown record type '") + Twine(int{Type}) + "'",
-          std::make_error_code(std::errc::executable_format_error));
-    }
-    Record.FuncId = RecordExtractor.getSigned(&OffsetPtr, sizeof(int32_t));
-    Record.TSC = RecordExtractor.getU64(&OffsetPtr);
-    Record.TId = RecordExtractor.getU32(&OffsetPtr);
-  }
-  return Error::success();
-}
-
-Error llvm::xray::YAMLLogLoader(StringRef Data, XRayFileHeader &FileHeader,
-                                std::vector<XRayRecord> &Records) {
-
-  // Load the documents from the MappedFile.
-  YAMLXRayTrace Trace;
-  Input In(Data);
-  In >> Trace;
-  if (In.error())
-    return make_error<StringError>("Failed loading YAML Data.", In.error());
-
-  FileHeader.Version = Trace.Header.Version;
-  FileHeader.Type = Trace.Header.Type;
-  FileHeader.ConstantTSC = Trace.Header.ConstantTSC;
-  FileHeader.NonstopTSC = Trace.Header.NonstopTSC;
-  FileHeader.CycleFrequency = Trace.Header.CycleFrequency;
-
-  if (FileHeader.Version != 1)
-    return make_error<StringError>(
-        Twine("Unsupported XRay file version: ") + Twine(FileHeader.Version),
-        std::make_error_code(std::errc::invalid_argument));
-
-  Records.clear();
-  std::transform(Trace.Records.begin(), Trace.Records.end(),
-                 std::back_inserter(Records), [&](const YAMLXRayRecord &R) {
-                   return XRayRecord{R.RecordType, R.CPU, R.Type,
-                                     R.FuncId,     R.TSC, R.TId};
-                 });
-  return Error::success();
-}
diff --git a/llvm/tools/llvm-xray/xray-log-reader.h b/llvm/tools/llvm-xray/xray-log-reader.h
deleted file mode 100644
index 4dd544328cf..00000000000
--- a/llvm/tools/llvm-xray/xray-log-reader.h
+++ /dev/null
@@ -1,57 +0,0 @@
-//===- xray-log-reader.h - XRay Log Reader Interface ----------------------===//
-//
-//                     The LLVM Compiler Infrastructure
-//
-// This file is distributed under the University of Illinois Open Source
-// License. See LICENSE.TXT for details.
-//
-//===----------------------------------------------------------------------===//
-//
-// Define the interface for an XRay log reader. Currently we only support one
-// version of the log (naive log) with fixed-sized records.
-//
-//===----------------------------------------------------------------------===//
-#ifndef LLVM_TOOLS_LLVM_XRAY_XRAY_LOG_READER_H
-#define LLVM_TOOLS_LLVM_XRAY_XRAY_LOG_READER_H
-
-#include <cstdint>
-#include <deque>
-#include <vector>
-
-#include "xray-record-yaml.h"
-#include "xray-record.h"
-#include "llvm/Support/Error.h"
-#include "llvm/Support/FileSystem.h"
-
-namespace llvm {
-namespace xray {
-
-class LogReader {
-  XRayFileHeader FileHeader;
-  std::vector<XRayRecord> Records;
-
-  typedef std::vector<XRayRecord>::const_iterator citerator;
-
-public:
-  typedef std::function<Error(StringRef, XRayFileHeader &,
-                              std::vector<XRayRecord> &)>
-      LoaderFunction;
-
-  LogReader(StringRef Filename, Error &Err, bool Sort, LoaderFunction Loader);
-
-  const XRayFileHeader &getFileHeader() const { return FileHeader; }
-
-  citerator begin() const { return Records.begin(); }
-  citerator end() const { return Records.end(); }
-  size_t size() const { return Records.size(); }
-};
-
-Error NaiveLogLoader(StringRef Data, XRayFileHeader &FileHeader,
-                     std::vector<XRayRecord> &Records);
-Error YAMLLogLoader(StringRef Data, XRayFileHeader &FileHeader,
-                    std::vector<XRayRecord> &Records);
-
-} // namespace xray
-} // namespace llvm
-
-#endif // LLVM_TOOLS_LLVM_XRAY_XRAY_LOG_READER_H
diff --git a/llvm/tools/llvm-xray/xray-record-yaml.h b/llvm/tools/llvm-xray/xray-record-yaml.h
deleted file mode 100644
index abce8ff60a9..00000000000
--- a/llvm/tools/llvm-xray/xray-record-yaml.h
+++ /dev/null
@@ -1,102 +0,0 @@
-//===- xray-record-yaml.h - XRay Record YAML Support Definitions ----------===//
-//
-//                     The LLVM Compiler Infrastructure
-//
-// This file is distributed under the University of Illinois Open Source
-// License. See LICENSE.TXT for details.
-//
-//===----------------------------------------------------------------------===//
-//
-// Types and traits specialisations for YAML I/O of XRay log entries.
-//
-//===----------------------------------------------------------------------===//
-#ifndef LLVM_TOOLS_LLVM_XRAY_XRAY_RECORD_YAML_H
-#define LLVM_TOOLS_LLVM_XRAY_XRAY_RECORD_YAML_H
-
-#include <type_traits>
-
-#include "xray-record.h"
-#include "llvm/Support/YAMLTraits.h"
-
-namespace llvm {
-namespace xray {
-
-struct YAMLXRayFileHeader {
-  uint16_t Version;
-  uint16_t Type;
-  bool ConstantTSC;
-  bool NonstopTSC;
-  uint64_t CycleFrequency;
-};
-
-struct YAMLXRayRecord {
-  uint16_t RecordType;
-  uint8_t CPU;
-  RecordTypes Type;
-  int32_t FuncId;
-  std::string Function;
-  uint64_t TSC;
-  uint32_t TId;
-};
-
-struct YAMLXRayTrace {
-  YAMLXRayFileHeader Header;
-  std::vector<YAMLXRayRecord> Records;
-};
-
-using XRayRecordStorage =
-    std::aligned_storage<sizeof(XRayRecord), alignof(XRayRecord)>::type;
-
-} // namespace xray
-
-namespace yaml {
-
-// YAML Traits
-// -----------
-template <> struct ScalarEnumerationTraits<xray::RecordTypes> {
-  static void enumeration(IO &IO, xray::RecordTypes &Type) {
-    IO.enumCase(Type, "function-enter", xray::RecordTypes::ENTER);
-    IO.enumCase(Type, "function-exit", xray::RecordTypes::EXIT);
-  }
-};
-
-template <> struct MappingTraits<xray::YAMLXRayFileHeader> {
-  static void mapping(IO &IO, xray::YAMLXRayFileHeader &Header) {
-    IO.mapRequired("version", Header.Version);
-    IO.mapRequired("type", Header.Type);
-    IO.mapRequired("constant-tsc", Header.ConstantTSC);
-    IO.mapRequired("nonstop-tsc", Header.NonstopTSC);
-    IO.mapRequired("cycle-frequency", Header.CycleFrequency);
-  }
-};
-
-template <> struct MappingTraits<xray::YAMLXRayRecord> {
-  static void mapping(IO &IO, xray::YAMLXRayRecord &Record) {
-    // FIXME: Make this type actually be descriptive
-    IO.mapRequired("type", Record.RecordType);
-    IO.mapRequired("func-id", Record.FuncId);
-    IO.mapOptional("function", Record.Function);
-    IO.mapRequired("cpu", Record.CPU);
-    IO.mapRequired("thread", Record.TId);
-    IO.mapRequired("kind", Record.Type);
-    IO.mapRequired("tsc", Record.TSC);
-  }
-
-  static constexpr bool flow = true;
-};
-
-template <> struct MappingTraits<xray::YAMLXRayTrace> {
-  static void mapping(IO &IO, xray::YAMLXRayTrace &Trace) {
-    // A trace file contains two parts, the header and the list of all the
-    // trace records.
-    IO.mapRequired("header", Trace.Header);
-    IO.mapRequired("records", Trace.Records);
-  }
-};
-
-} // namespace yaml
-} // namespace llvm
-
-LLVM_YAML_IS_SEQUENCE_VECTOR(xray::YAMLXRayRecord) 
-
-#endif // LLVM_TOOLS_LLVM_XRAY_XRAY_RECORD_YAML_H
diff --git a/llvm/tools/llvm-xray/xray-record.h b/llvm/tools/llvm-xray/xray-record.h
deleted file mode 100644
index 4a794d1dcfa..00000000000
--- a/llvm/tools/llvm-xray/xray-record.h
+++ /dev/null
@@ -1,55 +0,0 @@
-//===- xray-record.h - XRay Trace Record ----------------------------------===//
-//
-//                     The LLVM Compiler Infrastructure
-//
-// This file is distributed under the University of Illinois Open Source
-// License. See LICENSE.TXT for details.
-//
-//===----------------------------------------------------------------------===//
-//
-// This file replicates the record definition for XRay log entries. This should
-// follow the evolution of the log record versions supported in the compiler-rt
-// xray project.
-//
-//===----------------------------------------------------------------------===//
-#ifndef LLVM_TOOLS_LLVM_XRAY_XRAY_RECORD_H
-#define LLVM_TOOLS_LLVM_XRAY_XRAY_RECORD_H
-
-#include <cstdint>
-
-namespace llvm {
-namespace xray {
-
-struct XRayFileHeader {
-  uint16_t Version = 0;
-  uint16_t Type = 0;
-  bool ConstantTSC;
-  bool NonstopTSC;
-  uint64_t CycleFrequency = 0;
-};
-
-enum class RecordTypes { ENTER, EXIT };
-
-struct XRayRecord {
-  uint16_t RecordType;
-
-  // The CPU where the thread is running. We assume number of CPUs <= 256.
-  uint8_t CPU;
-
-  // Identifies the type of record.
-  RecordTypes Type;
-
-  // The function ID for the record.
-  int32_t FuncId;
-
-  // Get the full 8 bytes of the TSC when we get the log record.
-  uint64_t TSC;
-
-  // The thread ID for the currently running thread.
-  uint32_t TId;
-};
-
-} // namespace xray
-} // namespace llvm
-
-#endif // LLVM_TOOLS_LLVM_XRAY_XRAY_RECORD_H