Insert random noops to increase security against ROP attacks (clang)

A pass that adds random noops to X86 binaries to introduce diversity with the goal of increasing security against most return-oriented programming attacks.

Command line options:
  -noop-insertion // Enable noop insertion.
  -noop-insertion-percentage=X // X% of assembly instructions will have a noop prepended (default: 50%, requires -noop-insertion)
  -max-noops-per-instruction=X // Randomly generate X noops per instruction. ie. roll the dice X times with probability set above (default: 1). This doesn't guarantee X noop instructions.

In addition, the following 'quick switch' in clang enables basic diversity using default settings (currently: noop insertion and schedule randomization; it is intended to be extended in the future).
  -fdiversify

This is the clang part of the patch.
llvm part: D3392

http://reviews.llvm.org/D3393
Patch by Stephen Crane (@rinon)

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@225910 91177308-0d34-0410-b5e6-96231b3b80d8

6 files changed, 19 insertions, 1 deletions

diff --git a/include/clang/Driver/CC1Options.td b/include/clang/Driver/CC1Options.td
index e043001410..fafd149d47 100644
--- a/include/clang/Driver/CC1Options.td
+++ b/include/clang/Driver/CC1Options.td
@@ -194,6 +194,8 @@ def relaxed_aliasing : Flag<["-"], "relaxed-aliasing">,
   HelpText<"Turn off Type Based Alias Analysis">;
 def no_struct_path_tbaa : Flag<["-"], "no-struct-path-tbaa">,
   HelpText<"Turn off struct-path aware Type Based Alias Analysis">;
+def noop_insertion : Flag<["-"], "noop-insertion">,
+  HelpText<"Randomly insert NOOPs">;
 def masm_verbose : Flag<["-"], "masm-verbose">,
   HelpText<"Generate verbose assembly output">;
 def mcode_model : Separate<["-"], "mcode-model">,
diff --git a/include/clang/Driver/Options.td b/include/clang/Driver/Options.td
index 4daddba332..9a76d2a7b9 100644
--- a/include/clang/Driver/Options.td
+++ b/include/clang/Driver/Options.td
@@ -469,6 +469,7 @@ def fdiagnostics_show_category_EQ : Joined<["-"], "fdiagnostics-show-category=">
 def fdiagnostics_show_template_tree : Flag<["-"], "fdiagnostics-show-template-tree">,
     Group<f_Group>, Flags<[CC1Option]>,
     HelpText<"Print a template comparison tree for differing templates">;
+def fdiversify : Flag<["-"], "fdiversify">, Group<f_clang_Group>;
 def fdollars_in_identifiers : Flag<["-"], "fdollars-in-identifiers">, Group<f_Group>,
   HelpText<"Allow '$' in identifiers">, Flags<[CC1Option]>;
 def fdwarf2_cfi_asm : Flag<["-"], "fdwarf2-cfi-asm">, Group<clang_ignored_f_Group>;
@@ -857,7 +858,7 @@ def fprofile_arcs : Flag<["-"], "fprofile-arcs">, Group<f_Group>;
 def fno_profile_arcs : Flag<["-"], "fno-profile-arcs">, Group<f_Group>;
 def fprofile_generate : Flag<["-"], "fprofile-generate">, Group<f_Group>;
 def framework : Separate<["-"], "framework">, Flags<[LinkerInput]>;
-def frandom_seed_EQ : Joined<["-"], "frandom-seed=">, Group<clang_ignored_f_Group>;
+def frandom_seed_EQ : Joined<["-"], "frandom-seed=">, Group<f_Group>, Flags<[CC1Option]>;
 def freg_struct_return : Flag<["-"], "freg-struct-return">, Group<f_Group>, Flags<[CC1Option]>,
   HelpText<"Override the default ABI to return small structs in registers">;
 def frtti : Flag<["-"], "frtti">, Group<f_Group>;
diff --git a/include/clang/Frontend/CodeGenOptions.def b/include/clang/Frontend/CodeGenOptions.def
index b44672d0f5..5a9bfc4360 100644
--- a/include/clang/Frontend/CodeGenOptions.def
+++ b/include/clang/Frontend/CodeGenOptions.def
@@ -160,6 +160,8 @@ ENUM_CODEGENOPT(Inlining, InliningMethod, 2, NoInlining)
 /// The default TLS model to use.
 ENUM_CODEGENOPT(DefaultTLSModel, TLSModel, 2, GeneralDynamicTLSModel)
 
+CODEGENOPT(NoopInsertion, 1, 0) ///< Randomly add NOPs
+
 #undef CODEGENOPT
 #undef ENUM_CODEGENOPT
 #undef VALUE_CODEGENOPT
diff --git a/lib/CodeGen/BackendUtil.cpp b/lib/CodeGen/BackendUtil.cpp
index 25ecec5862..ef857ce7c9 100644
--- a/lib/CodeGen/BackendUtil.cpp
+++ b/lib/CodeGen/BackendUtil.cpp
@@ -519,6 +519,7 @@ TargetMachine *EmitAssemblyHelper::CreateTargetMachine(bool MustCreateTM) {
   Options.PositionIndependentExecutable = LangOpts.PIELevel != 0;
   Options.FunctionSections = CodeGenOpts.FunctionSections;
   Options.DataSections = CodeGenOpts.DataSections;
+  Options.NoopInsertion = CodeGenOpts.NoopInsertion;
 
   Options.MCOptions.MCRelaxAll = CodeGenOpts.RelaxAll;
   Options.MCOptions.MCSaveTempLabels = CodeGenOpts.SaveTempLabels;
diff --git a/lib/Driver/Tools.cpp b/lib/Driver/Tools.cpp
index d625c0e3e2..4aecf22468 100644
--- a/lib/Driver/Tools.cpp
+++ b/lib/Driver/Tools.cpp
@@ -3737,6 +3737,17 @@ void Clang::ConstructJob(Compilation &C, const JobAction &JA,
       getToolChain().getTriple().getArch() == llvm::Triple::aarch64_be)
     CmdArgs.push_back("-fallow-half-arguments-and-returns");
 
+  // Translate -frandom-seed to seed the LLVM RNG
+  if (Args.hasArg(options::OPT_frandom_seed_EQ)) {
+    StringRef seed = Args.getLastArgValue(options::OPT_frandom_seed_EQ);
+    CmdArgs.push_back("-backend-option");
+    CmdArgs.push_back(Args.MakeArgString("-rng-seed=" + seed));
+  }
+
+  if (Args.hasArg(options::OPT_fdiversify)) {
+    CmdArgs.push_back("-noop-insertion");
+  }
+
   if (Arg *A = Args.getLastArg(options::OPT_mrestrict_it,
                                options::OPT_mno_restrict_it)) {
     if (A->getOption().matches(options::OPT_mrestrict_it)) {
diff --git a/lib/Frontend/CompilerInvocation.cpp b/lib/Frontend/CompilerInvocation.cpp
index 0f6f01d0a0..ef8b76fa3f 100644
--- a/lib/Frontend/CompilerInvocation.cpp
+++ b/lib/Frontend/CompilerInvocation.cpp
@@ -516,6 +516,7 @@ static bool ParseCodeGenArgs(CodeGenOptions &Opts, ArgList &Args, InputKind IK,
   Opts.SSPBufferSize =
       getLastArgIntValue(Args, OPT_stack_protector_buffer_size, 8, Diags);
   Opts.StackRealignment = Args.hasArg(OPT_mstackrealign);
+  Opts.NoopInsertion = Args.hasArg(OPT_noop_insertion);
   if (Arg *A = Args.getLastArg(OPT_mstack_alignment)) {
     StringRef Val = A->getValue();
     unsigned StackAlignment = Opts.StackAlignment;