[BOLT] Introduce binary analysis tool based on BOLT (llvm#115330)

kbeyls · web-flow · commit ceb7214be028 · 2024-12-12T10:06:27.000Z
This initial commit does not add any specific binary analyses yet, it merely contains the boilerplate to introduce a new BOLT-based tool. This basically combines the 4 first patches from the prototype pac-ret and stack-clash binary analyzer discussed in RFC https://discourse.llvm.org/t/rfc-bolt-based-binary-analysis-tool-to-verify-correctness-of-security-hardening/78148 and published at llvm/llvm-project@main...kbeyls:llvm-project:bolt-gadget-scanner-prototype The introduction of such a BOLT-based binary analysis tool was proposed and discussed in at least the following places: - The RFC pointed to above - EuroLLVM 2024 round table https://discourse.llvm.org/t/summary-of-bolt-as-a-binary-analysis-tool-round-table-at-eurollvm/78441 The round table showed quite a few people interested in being able to build a custom binary analysis quickly with a tool like this. - Also at the US LLVM dev meeting a few weeks ago, I heard interest from a few people, asking when the tool would be available upstream. - The presentation "Adding Pointer Authentication ABI support for your ELF platform" (https://llvm.swoogo.com/2024devmtg/session/2512720/adding-pointer-authentication-abi-support-for-your-elf-platform) explicitly mentioned interest to extend the prototype tool to verify correct implementation of pauthabi.
diff --git a/bolt/docs/BinaryAnalysis.md b/bolt/docs/BinaryAnalysis.md
@@ -0,0 +1,20 @@
+# BOLT-based binary analysis
+
+As part of post-link-time optimizing, BOLT needs to perform a range of analyses
+on binaries such as recontructing control flow graphs, and more.
+
+The `llvm-bolt-binary-analysis` tool enables running requested binary analyses
+on binaries, and generating reports. It does this by building on top of the
+analyses implemented in the BOLT libraries.
+
+## Which binary analyses are implemented?
+
+At the moment, no binary analyses are implemented.
+
+The goal is to make it easy using a plug-in framework to add your own analyses.
+
+## How to add your own binary analysis
+
+_TODO: this section needs to be written. Ideally, we should have a simple
+"example" or "template" analysis that can be the starting point for implementing
+custom analyses_
diff --git a/bolt/include/bolt/Rewrite/RewriteInstance.h b/bolt/include/bolt/Rewrite/RewriteInstance.h
@@ -164,6 +164,9 @@ class RewriteInstance {
 
   void preregisterSections();
 
+  /// run analyses requested in binary analysis mode.
+  void runBinaryAnalyses();
+
   /// Run optimizations that operate at the binary, or post-linker, level.
   void runOptimizationPasses();
 
diff --git a/bolt/include/bolt/Utils/CommandLineOpts.h b/bolt/include/bolt/Utils/CommandLineOpts.h
@@ -18,6 +18,7 @@
 namespace opts {
 
 extern bool HeatmapMode;
+extern bool BinaryAnalysisMode;
 
 extern llvm::cl::OptionCategory BoltCategory;
 extern llvm::cl::OptionCategory BoltDiffCategory;
@@ -27,6 +28,7 @@ extern llvm::cl::OptionCategory BoltOutputCategory;
 extern llvm::cl::OptionCategory AggregatorCategory;
 extern llvm::cl::OptionCategory BoltInstrCategory;
 extern llvm::cl::OptionCategory HeatmapCategory;
+extern llvm::cl::OptionCategory BinaryAnalysisCategory;
 
 extern llvm::cl::opt<unsigned> AlignText;
 extern llvm::cl::opt<unsigned> AlignFunctions;
diff --git a/bolt/lib/Rewrite/RewriteInstance.cpp b/bolt/lib/Rewrite/RewriteInstance.cpp
@@ -699,6 +699,11 @@ Error RewriteInstance::run() {
   if (opts::DiffOnly)
     return Error::success();
 
+  if (opts::BinaryAnalysisMode) {
+    runBinaryAnalyses();
+    return Error::success();
+  }
+
   preregisterSections();
 
   runOptimizationPasses();
@@ -3475,6 +3480,8 @@ void RewriteInstance::runOptimizationPasses() {
   BC->logBOLTErrorsAndQuitOnFatal(BinaryFunctionPassManager::runAllPasses(*BC));
 }
 
+void RewriteInstance::runBinaryAnalyses() {}
+
 void RewriteInstance::preregisterSections() {
   // Preregister sections before emission to set their order in the output.
   const unsigned ROFlags = BinarySection::getFlags(/*IsReadOnly*/ true,
diff --git a/bolt/lib/Utils/CommandLineOpts.cpp b/bolt/lib/Utils/CommandLineOpts.cpp
@@ -29,6 +29,7 @@ const char *BoltRevision =
 namespace opts {
 
 bool HeatmapMode = false;
+bool BinaryAnalysisMode = false;
 
 cl::OptionCategory BoltCategory("BOLT generic options");
 cl::OptionCategory BoltDiffCategory("BOLTDIFF generic options");
@@ -38,6 +39,7 @@ cl::OptionCategory BoltOutputCategory("Output options");
 cl::OptionCategory AggregatorCategory("Data aggregation options");
 cl::OptionCategory BoltInstrCategory("BOLT instrumentation options");
 cl::OptionCategory HeatmapCategory("Heatmap options");
+cl::OptionCategory BinaryAnalysisCategory("BinaryAnalysis options");
 
 cl::opt<unsigned> AlignText("align-text",
                             cl::desc("alignment of .text section"), cl::Hidden,
diff --git a/bolt/test/CMakeLists.txt b/bolt/test/CMakeLists.txt
@@ -37,6 +37,7 @@ list(APPEND BOLT_TEST_DEPS
   lld
   llvm-config
   llvm-bolt
+  llvm-bolt-binary-analysis
   llvm-bolt-heatmap
   llvm-bat-dump
   llvm-dwarfdump
diff --git a/bolt/test/binary-analysis/AArch64/Inputs/dummy.txt b/bolt/test/binary-analysis/AArch64/Inputs/dummy.txt
@@ -0,0 +1 @@
+dummy
diff --git a/bolt/test/binary-analysis/AArch64/cmdline-args.test b/bolt/test/binary-analysis/AArch64/cmdline-args.test
@@ -0,0 +1,33 @@
+# This file tests error messages produced on invalid command line arguments.
+# It also checks that help messages are generated as expected.
+
+# Verify that an error message is provided if an input file is missing or incorrect
+
+RUN: not llvm-bolt-binary-analysis 2>&1 | FileCheck -check-prefix=NOFILEARG %s
+NOFILEARG:       llvm-bolt-binary-analysis: Not enough positional command line arguments specified!
+NOFILEARG-NEXT:  Must specify at least 1 positional argument: See: {{.*}}llvm-bolt-binary-analysis --help
+
+RUN: not llvm-bolt-binary-analysis non-existing-file 2>&1 | FileCheck -check-prefix=NONEXISTINGFILEARG %s
+NONEXISTINGFILEARG:       llvm-bolt-binary-analysis: 'non-existing-file': No such file or directory.
+
+RUN: not llvm-bolt-binary-analysis %p/Inputs/dummy.txt 2>&1 | FileCheck -check-prefix=NOELFFILEARG %s
+NOELFFILEARG:       llvm-bolt-binary-analysis: '{{.*}}/Inputs/dummy.txt': The file was not recognized as a valid object file.
+
+RUN: %clang %cflags %p/../../Inputs/asm_foo.s %p/../../Inputs/asm_main.c -o %t.exe
+RUN: llvm-bolt-binary-analysis %t.exe 2>&1 | FileCheck -check-prefix=VALIDELFFILEARG --allow-empty %s
+# Check that there are no BOLT-WARNING or BOLT-ERROR output lines
+VALIDELFFILEARG:     BOLT-INFO:
+VALIDELFFILEARG-NOT: BOLT-WARNING:
+VALIDELFFILEARG-NOT: BOLT-ERROR:
+
+# Check --help output
+
+RUN: llvm-bolt-binary-analysis --help 2>&1 | FileCheck -check-prefix=HELP %s
+
+HELP:       OVERVIEW: BinaryAnalysis
+HELP-EMPTY:
+HELP-NEXT:  USAGE: llvm-bolt-binary-analysis [options] <executable>
+HELP-EMPTY:
+HELP-NEXT:  OPTIONS:
+HELP-EMPTY:
+HELP-NEXT:  Generic Options:
diff --git a/bolt/test/binary-analysis/AArch64/lit.local.cfg b/bolt/test/binary-analysis/AArch64/lit.local.cfg
@@ -0,0 +1,7 @@
+if "AArch64" not in config.root.targets:
+    config.unsupported = True
+
+flags = "--target=aarch64-linux-gnu -nostartfiles -nostdlib -ffreestanding -Wl,--emit-relocs"
+
+config.substitutions.insert(0, ("%cflags", f"%cflags {flags}"))
+config.substitutions.insert(0, ("%cxxflags", f"%cxxflags {flags}"))
diff --git a/bolt/test/lit.cfg.py b/bolt/test/lit.cfg.py
@@ -110,6 +110,7 @@
     ),
     ToolSubst("llvm-boltdiff", unresolved="fatal"),
     ToolSubst("llvm-bolt-heatmap", unresolved="fatal"),
+    ToolSubst("llvm-bolt-binary-analysis", unresolved="fatal"),
     ToolSubst("llvm-bat-dump", unresolved="fatal"),
     ToolSubst("perf2bolt", unresolved="fatal"),
     ToolSubst("yaml2obj", unresolved="fatal"),
diff --git a/bolt/tools/CMakeLists.txt b/bolt/tools/CMakeLists.txt
@@ -7,3 +7,4 @@ add_subdirectory(llvm-bolt-fuzzer)
 add_subdirectory(bat-dump)
 add_subdirectory(merge-fdata)
 add_subdirectory(heatmap)
+add_subdirectory(binary-analysis)
diff --git a/bolt/tools/binary-analysis/CMakeLists.txt b/bolt/tools/binary-analysis/CMakeLists.txt
@@ -0,0 +1,19 @@
+set(LLVM_LINK_COMPONENTS
+  ${LLVM_TARGETS_TO_BUILD}
+  MC
+  Object
+  Support
+  )
+
+add_bolt_tool(llvm-bolt-binary-analysis
+  binary-analysis.cpp
+  DISABLE_LLVM_LINK_LLVM_DYLIB
+  )
+
+target_link_libraries(llvm-bolt-binary-analysis
+  PRIVATE
+  LLVMBOLTRewrite
+  LLVMBOLTUtils
+  )
+
+add_dependencies(bolt llvm-bolt-binary-analysis)
diff --git a/bolt/tools/binary-analysis/binary-analysis.cpp b/bolt/tools/binary-analysis/binary-analysis.cpp
@@ -0,0 +1,122 @@
+//===- bolt/tools/binary-analysis/binary-analysis.cpp ---------------------===//
+//
+// 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
+//
+//===----------------------------------------------------------------------===//
+//
+// This is a generic binary analysis tool, where multiple different specific
+// binary analyses can be plugged in to. The binary analyses are mostly built
+// on top of BOLT components.
+//
+//===----------------------------------------------------------------------===//
+
+#include "bolt/Rewrite/RewriteInstance.h"
+#include "bolt/Utils/CommandLineOpts.h"
+#include "llvm/MC/TargetRegistry.h"
+#include "llvm/Object/Binary.h"
+#include "llvm/Object/ELFObjectFile.h"
+#include "llvm/Support/CommandLine.h"
+#include "llvm/Support/Errc.h"
+#include "llvm/Support/ManagedStatic.h"
+#include "llvm/Support/PrettyStackTrace.h"
+#include "llvm/Support/Program.h"
+#include "llvm/Support/Signals.h"
+#include "llvm/Support/TargetSelect.h"
+#include "llvm/Support/VirtualFileSystem.h"
+
+#define DEBUG_TYPE "bolt"
+
+using namespace llvm;
+using namespace object;
+using namespace bolt;
+
+namespace opts {
+
+static cl::OptionCategory *BinaryAnalysisCategories[] = {
+    &BinaryAnalysisCategory};
+
+static cl::opt<std::string> InputFilename(cl::Positional,
+                                          cl::desc("<executable>"),
+                                          cl::Required,
+                                          cl::cat(BinaryAnalysisCategory),
+                                          cl::sub(cl::SubCommand::getAll()));
+
+} // namespace opts
+
+static StringRef ToolName = "llvm-bolt-binary-analysis";
+
+static void report_error(StringRef Message, std::error_code EC) {
+  assert(EC);
+  errs() << ToolName << ": '" << Message << "': " << EC.message() << ".\n";
+  exit(1);
+}
+
+static void report_error(StringRef Message, Error E) {
+  assert(E);
+  errs() << ToolName << ": '" << Message << "': " << toString(std::move(E))
+         << ".\n";
+  exit(1);
+}
+
+void ParseCommandLine(int argc, char **argv) {
+  cl::HideUnrelatedOptions(ArrayRef(opts::BinaryAnalysisCategories));
+  // Register the target printer for --version.
+  cl::AddExtraVersionPrinter(TargetRegistry::printRegisteredTargetsForVersion);
+
+  cl::ParseCommandLineOptions(argc, argv, "BinaryAnalysis\n");
+}
+
+static std::string GetExecutablePath(const char *Argv0) {
+  SmallString<256> ExecutablePath(Argv0);
+  // Do a PATH lookup if Argv0 isn't a valid path.
+  if (!llvm::sys::fs::exists(ExecutablePath))
+    if (llvm::ErrorOr<std::string> P =
+            llvm::sys::findProgramByName(ExecutablePath))
+      ExecutablePath = *P;
+  return std::string(ExecutablePath.str());
+}
+
+int main(int argc, char **argv) {
+  // Print a stack trace if we signal out.
+  sys::PrintStackTraceOnErrorSignal(argv[0]);
+  PrettyStackTraceProgram X(argc, argv);
+
+  std::string ToolPath = GetExecutablePath(argv[0]);
+
+  llvm_shutdown_obj Y; // Call llvm_shutdown() on exit.
+
+  // Initialize targets and assembly printers/parsers.
+  llvm::InitializeAllTargetInfos();
+  llvm::InitializeAllTargetMCs();
+  llvm::InitializeAllAsmParsers();
+  llvm::InitializeAllDisassemblers();
+
+  llvm::InitializeAllTargets();
+  llvm::InitializeAllAsmPrinters();
+
+  ParseCommandLine(argc, argv);
+
+  opts::BinaryAnalysisMode = true;
+
+  if (!sys::fs::exists(opts::InputFilename))
+    report_error(opts::InputFilename, errc::no_such_file_or_directory);
+
+  Expected<OwningBinary<Binary>> BinaryOrErr =
+      createBinary(opts::InputFilename);
+  if (Error E = BinaryOrErr.takeError())
+    report_error(opts::InputFilename, std::move(E));
+  Binary &Binary = *BinaryOrErr.get().getBinary();
+
+  if (auto *e = dyn_cast<ELFObjectFileBase>(&Binary)) {
+    auto RIOrErr = RewriteInstance::create(e, argc, argv, ToolPath);
+    if (Error E = RIOrErr.takeError())
+      report_error(opts::InputFilename, std::move(E));
+    RewriteInstance &RI = *RIOrErr.get();
+    if (Error E = RI.run())
+      report_error(opts::InputFilename, std::move(E));
+  }
+
+  return EXIT_SUCCESS;
+}
