Add .bolt_info notes section containing BOLT revision and command line args.

Summary:
Optinally add a .bolt_info notes section containing BOLT revision and command line args.
The new section is controlled by the -add-bolt-info flag which is on by default.

(cherry picked from FBD5125890)

bolt/CMakeLists.txt

@@ -1,6 +1,49 @@
 add_subdirectory(merge-fdata)
 add_subdirectory(Passes)
 
+# Get the current git revision for BOLT.
+function(get_version ofn)
+  find_program(git_executable NAMES git git.exe git.cmd)
+  if (git_executable)
+    execute_process(COMMAND ${git_executable} rev-parse HEAD
+      WORKING_DIRECTORY ${LLVM_MAIN_SRC_DIR}
+      TIMEOUT 5
+      RESULT_VARIABLE git_result
+      OUTPUT_VARIABLE git_output)
+      if( git_result EQUAL 0 )
+        string(STRIP "${git_output}" git_ref_id)
+        set(BOLT_REVISION "${git_ref_id}")
+      endif()
+  endif()
+
+  # If we can't find a revision, set it to "<unknown>".
+  if (NOT BOLT_REVISION)
+    set(BOLT_REVISION "<unknown>")
+  endif()
+
+  add_custom_command(OUTPUT ${CMAKE_CURRENT_BINARY_DIR}/${ofn}
+    COMMAND echo '"${BOLT_REVISION}"' > ${CMAKE_CURRENT_BINARY_DIR}/${ofn}
+    COMMENT "Generating bogus ${ofn}..."
+  )
+
+  set(VERSION_OUTPUT ${CMAKE_CURRENT_BINARY_DIR}/${ofn} PARENT_SCOPE)
+
+  # `make clean' must remove all those generated files:
+  set_property(DIRECTORY APPEND
+    PROPERTY ADDITIONAL_MAKE_CLEAN_FILES ${ofn})
+  set_source_files_properties(${CMAKE_CURRENT_BINARY_DIR}/${ofn} PROPERTIES
+    GENERATED 1)
+endfunction()
+
+# Creates a public target for generating the revision file.
+function(add_public_gen_version_target target)
+  add_custom_target(${target} DEPENDS ${VERSION_OUTPUT})
+  set(LLVM_COMMON_DEPENDS ${LLVM_COMMON_DEPENDS} ${target} PARENT_SCOPE)
+endfunction()
+
+get_version(BoltRevision.inc)
+add_public_gen_version_target(GenBoltRevision)
+
 set(LLVM_LINK_COMPONENTS
   ${LLVM_TARGETS_TO_BUILD}
   BOLTPasses

bolt/RewriteInstance.cpp

@@ -51,6 +51,7 @@
 #include "llvm/Support/TargetSelect.h"
 #include "llvm/Support/TargetRegistry.h"
 #include "llvm/Support/ToolOutputFile.h"
+#include "llvm/Support/raw_ostream.h"
 #include "llvm/Target/TargetMachine.h"
 #include <algorithm>
 #include <fstream>
@@ -311,6 +312,13 @@ Verbosity("v",
   cl::ZeroOrMore,
   cl::cat(BoltCategory));
 
+static cl::opt<bool>
+AddBoltInfo("add-bolt-info",
+  cl::desc("add BOLT version and command line argument information to "
+           "processed binaries"),
+  cl::init(true),
+  cl::cat(BoltCategory));
+
 // Check against lists of functions from options if we should
 // optimize the function with a given name.
 bool shouldProcess(const BinaryFunction &Function) {
@@ -392,6 +400,12 @@ const std::string RewriteInstance::OrgSecPrefix = ".bolt.org";
 
 const std::string RewriteInstance::BOLTSecPrefix = ".bolt";
 
+namespace llvm {
+namespace bolt {
+extern const char *BoltRevision;
+}
+}
+
 static void report_error(StringRef Message, std::error_code EC) {
   assert(EC);
   errs() << "BOLT-ERROR: '" << Message << "': " << EC.message() << ".\n";
@@ -597,8 +611,12 @@ std::unique_ptr<BinaryContext> createBinaryContext(
 } // namespace
 
 RewriteInstance::RewriteInstance(ELFObjectFileBase *File,
-                                 const DataReader &DR)
+                                 const DataReader &DR,
+                                 const int Argc,
+                                 const char *const *Argv)
     : InputFile(File),
+      Argc(Argc),
+      Argv(Argv),
       BC(createBinaryContext("x86-64", "x86_64-unknown-linux", DR,
          std::unique_ptr<DWARFContext>(
            new DWARFContextInMemory(*InputFile, nullptr, true)))) {
@@ -796,6 +814,8 @@ void RewriteInstance::run() {
   if (opts::UpdateDebugSections)
     updateDebugInfo();
 
+  addBoltInfoSection();
+
   // Copy allocatable part of the input.
   std::error_code EC;
   Out = llvm::make_unique<tool_output_file>(opts::OutputFilename, EC,
@@ -2765,6 +2785,30 @@ void RewriteInstance::finalizeSectionStringTable(ELFObjectFile<ELFT> *File) {
   EFMM->NoteSectionInfo[".shstrtab"].IsStrTab = true;
 }
 
+void RewriteInstance::addBoltInfoSection() {
+  if (opts::AddBoltInfo) {
+    std::string Str;
+    raw_string_ostream OS(Str);
+
+    OS << "BOLT revision: " << BoltRevision << ", " << "command line:";
+    for (auto I = 0; I < Argc; ++I) {
+      OS << " " << Argv[I];
+    }
+
+    const auto BoltInfo = OS.str();
+    const auto SectionSize = BoltInfo.size();
+    uint8_t *SectionData = new uint8_t[SectionSize];
+    memcpy(SectionData, BoltInfo.data(), SectionSize);
+    EFMM->NoteSectionInfo[".bolt_info"] =
+      SectionInfo(reinterpret_cast<uint64_t>(SectionData),
+                  SectionSize,
+                  /*Alignment=*/1,
+                  /*IsCode=*/false,
+                  /*IsReadOnly=*/true,
+                  /*IsLocal=*/false);
+  }
+}
+
 // Rewrite section header table inserting new entries as needed. The sections
 // header table size itself may affect the offsets of other sections,
 // so we are placing it at the end of the binary.

bolt/RewriteInstance.h

@@ -146,7 +146,8 @@ public:
 /// events.
 class RewriteInstance {
 public:
-  RewriteInstance(llvm::object::ELFObjectFileBase *File, const DataReader &DR);
+  RewriteInstance(llvm::object::ELFObjectFileBase *File, const DataReader &DR,
+                  const int Argc, const char *const *Argv);
   ~RewriteInstance();
 
   /// Reset all state except for split hints. Used to run a second pass with
@@ -320,6 +321,9 @@ private:
   /// Finalize memory image of section header string table.
   ELF_FUNCTION(finalizeSectionStringTable);
 
+  /// Add a notes section containing the BOLT revision and command line options.
+  void addBoltInfoSection();
+
   /// Computes output .debug_line line table offsets for each compile unit,
   /// and updates stmt_list for a corresponding compile unit.
   void updateLineTableOffsets();
@@ -388,6 +392,10 @@ private:
   /// An instance of the input binary we are processing, externally owned.
   llvm::object::ELFObjectFileBase *InputFile;
 
+  /// Command line args used to process binary.
+  const int Argc;
+  const char *const *Argv;
+
   std::unique_ptr<BinaryContext> BC;
   std::unique_ptr<CFIReaderWriter> CFIRdWrt;
 

bolt/llvm-bolt.cpp

@@ -69,6 +69,18 @@ static void report_error(StringRef Message, std::error_code EC) {
   exit(1);
 }
 
+namespace llvm {
+namespace bolt {
+const char *BoltRevision =
+#include "BoltRevision.inc"
+;
+}
+}
+
+static void printBoltRevision() {
+  errs() << "BOLT revision " << BoltRevision << "\n";
+}
+
 int main(int argc, char **argv) {
   // Print a stack trace if we signal out.
   sys::PrintStackTraceOnErrorSignal();
@@ -88,6 +100,7 @@ int main(int argc, char **argv) {
   cl::HideUnrelatedOptions(makeArrayRef(opts::BoltCategories));
 
   // Register the target printer for --version.
+  cl::AddExtraVersionPrinter(printBoltRevision);
   cl::AddExtraVersionPrinter(TargetRegistry::printRegisteredTargetsForVersion);
 
   cl::ParseCommandLineOptions(argc, argv,
@@ -122,7 +135,7 @@ int main(int argc, char **argv) {
   Binary &Binary = *BinaryOrErr.get().getBinary();
 
   if (auto *e = dyn_cast<ELFObjectFileBase>(&Binary)) {
-    RewriteInstance RI(e, *DR.get());
+    RewriteInstance RI(e, *DR.get(), argc, argv);
     RI.run();
   } else {
     report_error(opts::InputFilename, object_error::invalid_file_type);