[randstruct] Add randomize structure layout support

The Randstruct feature is a compile-time hardening technique that
randomizes the field layout for designated structures of a code base.
Admittedly, this is mostly useful for closed-source releases of code,
since the randomization seed would need to be available for public and
open source applications.

Why implement it? This patch set enhances Clang’s feature parity with
that of GCC which already has the Randstruct feature. It's used by the
Linux kernel in certain structures to help thwart attacks that depend on
structure layouts in memory.

This patch set is a from-scratch reimplementation of the Randstruct
feature that was originally ported to GCC. The patches for the GCC
implementation can be found here:

  https://www.openwall.com/lists/kernel-hardening/2017/04/06/14

Link: https://lists.llvm.org/pipermail/cfe-dev/2019-March/061607.html
Co-authored-by: Cole Nixon <nixontcole@gmail.com>
Co-authored-by: Connor Kuehl <cipkuehl@gmail.com>
Co-authored-by: James Foster <jafosterja@gmail.com>
Co-authored-by: Jeff Takahashi <jeffrey.takahashi@gmail.com>
Co-authored-by: Jordan Cantrell <jordan.cantrell@mail.com>
Co-authored-by: Nikk Forbus <nicholas.forbus@gmail.com>
Co-authored-by: Tim Pugh <nwtpugh@gmail.com>
Co-authored-by: Bill Wendling <isanbard@gmail.com>
Signed-off-by: Bill Wendling <isanbard@gmail.com>

Reviewed By: aaron.ballman

Differential Revision: https://reviews.llvm.org/D121556

clang/docs/ReleaseNotes.rst

@@ -54,6 +54,20 @@ Major New Features
   There is an analogous ``zero_call_used_regs`` attribute to allow for finer
   control of this feature.
 
+- Clang now supports randomizing structure layout in C. This feature is a
+  compile-time hardening technique, making it more difficult for an attacker to
+  retrieve data from structures. Specify randomization with the
+  ``randomize_layout`` attribute. The corresponding ``no_randomize_layout``
+  attribute can be used to turn the feature off.
+
+  A seed value is required to enable randomization, and is deterministic based
+  on a seed value. Use the ``-frandomize-layout-seed=`` or
+  ``-frandomize-layout-seed-file=`` flags.
+
+  .. note::
+
+      Randomizing structure layout is a C-only feature.
+
 Bug Fixes
 ------------------
 - ``CXXNewExpr::getArraySize()`` previously returned a ``llvm::Optional``

clang/include/clang/AST/Decl.h

@@ -4051,6 +4051,12 @@ public:
     RecordDeclBits.ParamDestroyedInCallee = V;
   }
 
+  bool isRandomized() const { return RecordDeclBits.IsRandomized; }
+
+  void setIsRandomized(bool V) { RecordDeclBits.IsRandomized = V; }
+
+  void reorderFields(const SmallVectorImpl<Decl *> &Fields);
+
   /// Determines whether this declaration represents the
   /// injected class name.
   ///

clang/include/clang/AST/DeclBase.h

@@ -313,6 +313,7 @@ protected:
   friend class ASTReader;
   friend class CXXClassMemberWrapper;
   friend class LinkageComputer;
+  friend class RecordDecl;
   template<typename decl_type> friend class Redeclarable;
 
   /// Access - Used by C++ decls for the access specifier.
@@ -1540,10 +1541,13 @@ class DeclContext {
 
     /// Represents the way this type is passed to a function.
     uint64_t ArgPassingRestrictions : 2;
+
+    /// Indicates whether this struct has had its field layout randomized.
+    uint64_t IsRandomized : 1;
   };
 
   /// Number of non-inherited bits in RecordDeclBitfields.
-  enum { NumRecordDeclBits = 14 };
+  enum { NumRecordDeclBits = 15 };
 
   /// Stores the bits used by OMPDeclareReductionDecl.
   /// If modified NumOMPDeclareReductionDeclBits and the accessor

clang/include/clang/AST/Randstruct.h

@@ -0,0 +1,38 @@
+//===- Randstruct.h - Interfact for structure randomization -------*- C++ -*-=//
+//
+// 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 file contains the interface for Clang's structure field layout
+// randomization.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_CLANG_AST_RANDSTRUCT_H
+#define LLVM_CLANG_AST_RANDSTRUCT_H
+
+namespace llvm {
+template <typename T> class ArrayRef;
+template <typename T> class SmallVectorImpl;
+class StringRef;
+} // end namespace llvm
+
+namespace clang {
+
+class ASTContext;
+class Decl;
+class RecordDecl;
+
+namespace randstruct {
+
+bool randomizeStructureLayout(const ASTContext &Context, llvm::StringRef Name,
+                              llvm::ArrayRef<Decl *> Fields,
+                              llvm::SmallVectorImpl<Decl *> &FinalOrdering);
+
+} // namespace randstruct
+} // namespace clang
+
+#endif // LLVM_CLANG_AST_RANDSTRUCT_H

clang/include/clang/Basic/Attr.td

@@ -3957,3 +3957,18 @@ def HLSLNumThreads: InheritableAttr {
   let LangOpts = [HLSL];
   let Documentation = [NumThreadsDocs];
 }
+
+def RandomizeLayout : InheritableAttr {
+  let Spellings = [GCC<"randomize_layout">];
+  let Subjects = SubjectList<[Record]>;
+  let Documentation = [ClangRandomizeLayoutDocs];
+  let LangOpts = [COnly];
+}
+
+def NoRandomizeLayout : InheritableAttr {
+  let Spellings = [GCC<"no_randomize_layout">];
+  let Subjects = SubjectList<[Record]>;
+  let Documentation = [ClangRandomizeLayoutDocs];
+  let LangOpts = [COnly];
+}
+def : MutualExclusions<[RandomizeLayout, NoRandomizeLayout]>;

clang/include/clang/Basic/AttrDocs.td

@@ -6379,3 +6379,35 @@ dictate the thread id. Total number of threads executed is ``X * Y * Z``.
 The full documentation is available here: https://docs.microsoft.com/en-us/windows/win32/direct3dhlsl/sm5-attributes-numthreads
   }];
 }
+
+def ClangRandomizeLayoutDocs : Documentation {
+  let Category = DocCatDecl;
+  let Heading = "randomize_layout, no_randomize_layout";
+  let Content = [{
+The attribute ``randomize_layout``, when attached to a C structure, selects it
+for structure layout field randomization; a compile-time hardening technique. A
+"seed" value, is specified via the ``-frandomize-layout-seed=`` command line flag.
+For example:
+
+.. code-block:: bash
+
+  SEED=`od -A n -t x8 -N 32 /dev/urandom | tr -d ' \n'`
+  make ... CFLAGS="-frandomize-layout-seed=$SEED" ...
+
+You can also supply the seed in a file with ``-frandomize-layout-seed-file=``.
+For example:
+
+.. code-block:: bash
+
+  od -A n -t x8 -N 32 /dev/urandom | tr -d ' \n' > /tmp/seed_file.txt
+  make ... CFLAGS="-frandomize-layout-seed-file=/tmp/seed_file.txt" ...
+
+The randomization is deterministic based for a given seed, so the entire
+program should be compiled with the same seed, but keep the seed safe
+otherwise.
+
+The attribute ``no_randomize_layout``, when attached to a C structure,
+instructs the compiler that this structure should not have its field layout
+randomized.
+  }];
+}

clang/include/clang/Basic/DiagnosticDriverKinds.td

@@ -165,6 +165,8 @@ def err_drv_amdgpu_ieee_without_no_honor_nans : Error<
   "invalid argument '-mno-amdgpu-ieee' only allowed with relaxed NaN handling">;
 def err_drv_argument_not_allowed_with : Error<
   "invalid argument '%0' not allowed with '%1'">;
+def err_drv_cannot_open_randomize_layout_seed_file : Error<
+  "cannot read randomize layout seed file '%0'">;
 def err_drv_invalid_version_number : Error<
   "invalid version number in '%0'">;
 def err_drv_no_linker_llvm_support : Error<

clang/include/clang/Basic/DiagnosticSemaKinds.td

@@ -11588,5 +11588,7 @@ def err_hlsl_numthreads_argument_oor : Error<"argument '%select{X|Y|Z}0' to numt
 def err_hlsl_numthreads_invalid : Error<"total number of threads cannot exceed %0">;
 def err_hlsl_attribute_param_mismatch : Error<"%0 attribute parameters do not match the previous declaration">;
 
+// Layout randomization warning.
+def err_cast_from_randomized_struct : Error<
+  "casting from randomized structure pointer type %0 to %1">;
 } // end of sema component.
-

clang/include/clang/Basic/LangOptions.h

@@ -445,6 +445,9 @@ public:
   /// The default stream kind used for HIP kernel launching.
   GPUDefaultStreamKind GPUDefaultStream;
 
+  /// The seed used by the randomize structure layout feature.
+  std::string RandstructSeed;
+
   LangOptions();
 
   // Define accessors/mutators for language options of enumeration type.

clang/include/clang/Driver/Options.td

@@ -2122,6 +2122,12 @@ defm merge_all_constants : BoolFOption<"merge-all-constants",
 def fmessage_length_EQ : Joined<["-"], "fmessage-length=">, Group<f_Group>, Flags<[CC1Option]>,
   HelpText<"Format message diagnostics so that they fit within N columns">,
   MarshallingInfoInt<DiagnosticOpts<"MessageLength">>;
+def frandomize_layout_seed_EQ : Joined<["-"], "frandomize-layout-seed=">,
+  MetaVarName<"<seed>">, Group<f_clang_Group>, Flags<[CC1Option]>,
+  HelpText<"The seed used by the randomize structure layout feature">;
+def frandomize_layout_seed_file_EQ : Joined<["-"], "frandomize-layout-seed-file=">,
+  MetaVarName<"<file>">, Group<f_clang_Group>, Flags<[CC1Option]>,
+  HelpText<"File holding the seed used by the randomize structure layout feature">;
 def fms_compatibility : Flag<["-"], "fms-compatibility">, Group<f_Group>, Flags<[CC1Option, CoreOption]>,
   HelpText<"Enable full Microsoft Visual C++ compatibility">,
   MarshallingInfoFlag<LangOpts<"MSVCCompat">>;

clang/lib/AST/CMakeLists.txt

@@ -97,6 +97,7 @@ add_clang_library(clangAST
   ParentMap.cpp
   PrintfFormatString.cpp
   QualTypeNames.cpp
+  Randstruct.cpp
   RawCommentList.cpp
   RecordLayout.cpp
   RecordLayoutBuilder.cpp

clang/lib/AST/Decl.cpp

@@ -30,6 +30,7 @@
 #include "clang/AST/ODRHash.h"
 #include "clang/AST/PrettyDeclStackTrace.h"
 #include "clang/AST/PrettyPrinter.h"
+#include "clang/AST/Randstruct.h"
 #include "clang/AST/Redeclarable.h"
 #include "clang/AST/Stmt.h"
 #include "clang/AST/TemplateBase.h"
@@ -4583,6 +4584,7 @@ RecordDecl::RecordDecl(Kind DK, TagKind TK, const ASTContext &C,
   setHasNonTrivialToPrimitiveCopyCUnion(false);
   setParamDestroyedInCallee(false);
   setArgPassingRestrictions(APK_CanPassInRegs);
+  setIsRandomized(false);
 }
 
 RecordDecl *RecordDecl::Create(const ASTContext &C, TagKind TK, DeclContext *DC,
@@ -4666,6 +4668,12 @@ bool RecordDecl::isMsStruct(const ASTContext &C) const {
   return hasAttr<MSStructAttr>() || C.getLangOpts().MSBitfields == 1;
 }
 
+void RecordDecl::reorderFields(const SmallVectorImpl<Decl *> &Fields) {
+  std::tie(FirstDecl, LastDecl) = DeclContext::BuildDeclChain(Fields, false);
+  LastDecl->NextInContextAndBits.setPointer(nullptr);
+  setIsRandomized(true);
+}
+
 void RecordDecl::LoadFieldsFromExternalStorage() const {
   ExternalASTSource *Source = getASTContext().getExternalSource();
   assert(hasExternalLexicalStorage() && Source && "No external storage?");

clang/lib/AST/Randstruct.cpp

@@ -0,0 +1,223 @@
+//===--- Randstruct.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 file contains the implementation for Clang's structure field layout
+// randomization.
+//
+//===----------------------------------------------------------------------===//
+
+#include "clang/AST/Randstruct.h"
+#include "clang/AST/ASTContext.h"
+#include "clang/AST/ASTDiagnostic.h"
+#include "clang/AST/Attr.h"
+#include "clang/Basic/Diagnostic.h"
+#include "llvm/ADT/SmallVector.h"
+
+#include <algorithm>
+#include <random>
+#include <set>
+#include <sstream>
+#include <string>
+
+using clang::ASTContext;
+using clang::FieldDecl;
+using llvm::SmallVector;
+
+namespace {
+
+// FIXME: Replace this with some discovery once that mechanism exists.
+enum { CACHE_LINE = 64 };
+
+// The Bucket class holds the struct fields we're trying to fill to a
+// cache-line.
+class Bucket {
+  SmallVector<FieldDecl *, 64> Fields;
+  int Size = 0;
+
+public:
+  virtual ~Bucket() = default;
+
+  SmallVector<FieldDecl *, 64> &fields() { return Fields; }
+  void addField(FieldDecl *Field, int FieldSize);
+  virtual bool canFit(int FieldSize) const {
+    return Size + FieldSize <= CACHE_LINE;
+  }
+  virtual bool isBitfieldRun() const { return false; }
+  bool full() const { return Size >= CACHE_LINE; }
+};
+
+void Bucket::addField(FieldDecl *Field, int FieldSize) {
+  Size += FieldSize;
+  Fields.push_back(Field);
+}
+
+struct BitfieldRunBucket : public Bucket {
+  bool canFit(int FieldSize) const override { return true; }
+  bool isBitfieldRun() const override { return true; }
+};
+
+void randomizeStructureLayoutImpl(const ASTContext &Context,
+                                  llvm::SmallVectorImpl<FieldDecl *> &FieldsOut,
+                                  std::mt19937 &RNG) {
+  // All of the Buckets produced by best-effort cache-line algorithm.
+  SmallVector<std::unique_ptr<Bucket>, 16> Buckets;
+
+  // The current bucket of fields that we are trying to fill to a cache-line.
+  std::unique_ptr<Bucket> CurrentBucket;
+
+  // The current bucket containing the run of adjacent bitfields to ensure they
+  // remain adjacent.
+  std::unique_ptr<BitfieldRunBucket> CurrentBitfieldRun;
+
+  // Tracks the number of fields that we failed to fit to the current bucket,
+  // and thus still need to be added later.
+  size_t Skipped = 0;
+
+  while (!FieldsOut.empty()) {
+    // If we've Skipped more fields than we have remaining to place, that means
+    // that they can't fit in our current bucket, and we need to start a new
+    // one.
+    if (Skipped >= FieldsOut.size()) {
+      Skipped = 0;
+      Buckets.push_back(std::move(CurrentBucket));
+    }
+
+    // Take the first field that needs to be put in a bucket.
+    auto FieldIter = FieldsOut.begin();
+    FieldDecl *FD = *FieldIter;
+
+    if (FD->isBitField() && !FD->isZeroLengthBitField(Context)) {
+      // Start a bitfield run if this is the first bitfield we have found.
+      if (!CurrentBitfieldRun)
+        CurrentBitfieldRun = std::make_unique<BitfieldRunBucket>();
+
+      // We've placed the field, and can remove it from the "awaiting Buckets"
+      // vector called "Fields."
+      CurrentBitfieldRun->addField(FD, /*FieldSize is irrelevant here*/ 1);
+      FieldsOut.erase(FieldIter);
+      continue;
+    }
+
+    // Else, current field is not a bitfield. If we were previously in a
+    // bitfield run, end it.
+    if (CurrentBitfieldRun)
+      Buckets.push_back(std::move(CurrentBitfieldRun));
+
+    // If we don't have a bucket, make one.
+    if (!CurrentBucket)
+      CurrentBucket = std::make_unique<Bucket>();
+
+    uint64_t Width = Context.getTypeInfo(FD->getType()).Width;
+    if (Width >= CACHE_LINE) {
+      std::unique_ptr<Bucket> OverSized = std::make_unique<Bucket>();
+      OverSized->addField(FD, Width);
+      FieldsOut.erase(FieldIter);
+      Buckets.push_back(std::move(OverSized));
+      continue;
+    }
+
+    // If it fits, add it.
+    if (CurrentBucket->canFit(Width)) {
+      CurrentBucket->addField(FD, Width);
+      FieldsOut.erase(FieldIter);
+
+      // If it's now full, tie off the bucket.
+      if (CurrentBucket->full()) {
+        Skipped = 0;
+        Buckets.push_back(std::move(CurrentBucket));
+      }
+    } else {
+      // We can't fit it in our current bucket. Move to the end for processing
+      // later.
+      ++Skipped; // Mark it skipped.
+      FieldsOut.push_back(FD);
+      FieldsOut.erase(FieldIter);
+    }
+  }
+
+  // Done processing the fields awaiting a bucket.
+
+  // If we were filling a bucket, tie it off.
+  if (CurrentBucket)
+    Buckets.push_back(std::move(CurrentBucket));
+
+  // If we were processing a bitfield run bucket, tie it off.
+  if (CurrentBitfieldRun)
+    Buckets.push_back(std::move(CurrentBitfieldRun));
+
+  std::shuffle(std::begin(Buckets), std::end(Buckets), RNG);
+
+  // Produce the new ordering of the elements from the Buckets.
+  SmallVector<FieldDecl *, 16> FinalOrder;
+  for (const std::unique_ptr<Bucket> &B : Buckets) {
+    llvm::SmallVectorImpl<FieldDecl *> &RandFields = B->fields();
+    if (!B->isBitfieldRun())
+      std::shuffle(std::begin(RandFields), std::end(RandFields), RNG);
+
+    FinalOrder.insert(FinalOrder.end(), RandFields.begin(), RandFields.end());
+  }
+
+  FieldsOut = FinalOrder;
+}
+
+} // anonymous namespace
+
+namespace clang {
+namespace randstruct {
+
+bool randomizeStructureLayout(const ASTContext &Context, StringRef Name,
+                              ArrayRef<Decl *> Fields,
+                              SmallVectorImpl<Decl *> &FinalOrdering) {
+  SmallVector<FieldDecl *, 64> RandomizedFields;
+
+  unsigned TotalNumFields = 0;
+  for (Decl *D : Fields) {
+    ++TotalNumFields;
+    if (auto *FD = dyn_cast<FieldDecl>(D))
+      RandomizedFields.push_back(FD);
+    else
+      FinalOrdering.push_back(D);
+  }
+
+  if (RandomizedFields.empty())
+    return false;
+
+  // Struct might end with a variable-length array or an array of size 0 or 1,
+  // in which case we don't want to randomize it.
+  FieldDecl *VLA = nullptr;
+  const auto *CA =
+      dyn_cast<ConstantArrayType>(RandomizedFields.back()->getType());
+  if ((CA && (CA->getSize().sle(2) || CA->isIncompleteArrayType())) ||
+      llvm::any_of(Fields, [](Decl *D) {
+        if (const FieldDecl *FD = dyn_cast<FieldDecl>(D)) {
+          const Type *FDTy = FD->getType().getTypePtr();
+          if (const RecordType *FDTTy = FDTy->getAs<RecordType>())
+            return FDTTy->getDecl()->hasFlexibleArrayMember();
+        }
+        return false;
+      }))
+    VLA = RandomizedFields.pop_back_val();
+
+  std::string Seed = (Context.getLangOpts().RandstructSeed + Name).str();
+  std::seed_seq SeedSeq(Seed.begin(), Seed.end());
+  std::mt19937 RNG(SeedSeq);
+
+  randomizeStructureLayoutImpl(Context, RandomizedFields, RNG);
+  if (VLA)
+    RandomizedFields.push_back(VLA);
+
+  FinalOrdering.insert(FinalOrdering.end(), RandomizedFields.begin(),
+                       RandomizedFields.end());
+
+  assert(TotalNumFields == FinalOrdering.size() &&
+         "Decl count has been altered after Randstruct randomization!");
+  return true;
+}
+
+} // end namespace randstruct
+} // end namespace clang

clang/lib/Driver/ToolChains/Clang.cpp

@@ -5907,6 +5907,14 @@ void Clang::ConstructJob(Compilation &C, const JobAction &JA,
     CmdArgs.push_back(
         Args.MakeArgString("-fmessage-length=" + Twine(MessageLength)));
 
+  if (Arg *A = Args.getLastArg(options::OPT_frandomize_layout_seed_EQ))
+    CmdArgs.push_back(
+        Args.MakeArgString("-frandomize-layout-seed=" + Twine(A->getValue(0))));
+
+  if (Arg *A = Args.getLastArg(options::OPT_frandomize_layout_seed_file_EQ))
+    CmdArgs.push_back(Args.MakeArgString("-frandomize-layout-seed-file=" +
+                                         Twine(A->getValue(0))));
+
   // -fvisibility= and -fvisibility-ms-compat are of a piece.
   if (const Arg *A = Args.getLastArg(options::OPT_fvisibility_EQ,
                                      options::OPT_fvisibility_ms_compat)) {

clang/lib/Frontend/CompilerInvocation.cpp

@@ -94,6 +94,7 @@
 #include <cassert>
 #include <cstddef>
 #include <cstring>
+#include <fstream>
 #include <memory>
 #include <string>
 #include <tuple>
@@ -3685,6 +3686,9 @@ void CompilerInvocation::GenerateLangArgs(const LangOptions &Opts,
 
   for (const auto &MP : Opts.MacroPrefixMap)
     GenerateArg(Args, OPT_fmacro_prefix_map_EQ, MP.first + "=" + MP.second, SA);
+
+  if (!Opts.RandstructSeed.empty())
+    GenerateArg(Args, OPT_frandomize_layout_seed_EQ, Opts.RandstructSeed, SA);
 }
 
 bool CompilerInvocation::ParseLangArgs(LangOptions &Opts, ArgList &Args,
@@ -4237,6 +4241,19 @@ bool CompilerInvocation::ParseLangArgs(LangOptions &Opts, ArgList &Args,
       Diags.Report(diag::err_cc1_unbounded_vscale_min);
   }
 
+  if (const Arg *A = Args.getLastArg(OPT_frandomize_layout_seed_file_EQ)) {
+    std::ifstream SeedFile(A->getValue(0));
+
+    if (!SeedFile.is_open())
+      Diags.Report(diag::err_drv_cannot_open_randomize_layout_seed_file)
+          << A->getValue(0);
+
+    std::getline(SeedFile, Opts.RandstructSeed);
+  }
+
+  if (const Arg *A = Args.getLastArg(OPT_frandomize_layout_seed_EQ))
+    Opts.RandstructSeed = A->getValue(0);
+
   return Diags.getNumErrors() == NumErrorsBefore;
 }
 

clang/lib/Sema/SemaCast.cpp

@@ -3129,6 +3129,23 @@ void CastOperation::CheckCStyleCast() {
     Self.Diag(OpRange.getBegin(), diag::warn_cast_function_type)
         << SrcType << DestType << OpRange;
 
+  if (isa<PointerType>(SrcType) && isa<PointerType>(DestType)) {
+    QualType SrcTy = cast<PointerType>(SrcType)->getPointeeType();
+    QualType DestTy = cast<PointerType>(DestType)->getPointeeType();
+
+    const RecordDecl *SrcRD = SrcTy->getAsRecordDecl();
+    const RecordDecl *DestRD = DestTy->getAsRecordDecl();
+
+    if (SrcRD && DestRD && SrcRD->hasAttr<RandomizeLayoutAttr>() &&
+        SrcRD != DestRD) {
+      // The struct we are casting the pointer from was randomized.
+      Self.Diag(OpRange.getBegin(), diag::err_cast_from_randomized_struct)
+          << SrcType << DestType;
+      SrcExpr = ExprError();
+      return;
+    }
+  }
+
   DiagnoseCastOfObjCSEL(Self, SrcExpr, DestType);
   DiagnoseCallingConvCast(Self, SrcExpr, DestType, OpRange);
   DiagnoseBadFunctionCast(Self, SrcExpr, DestType);

clang/lib/Sema/SemaDecl.cpp

@@ -24,6 +24,7 @@
 #include "clang/AST/Expr.h"
 #include "clang/AST/ExprCXX.h"
 #include "clang/AST/NonTrivialTypeVisitor.h"
+#include "clang/AST/Randstruct.h"
 #include "clang/AST/StmtCXX.h"
 #include "clang/Basic/Builtins.h"
 #include "clang/Basic/PartialDiagnostic.h"
@@ -17968,6 +17969,18 @@ void Sema::ActOnFields(Scope *S, SourceLocation RecLoc, Decl *EnclosingDecl,
     // Handle attributes before checking the layout.
     ProcessDeclAttributeList(S, Record, Attrs);
 
+    // Maybe randomize the field order.
+    if (!getLangOpts().CPlusPlus && Record->hasAttr<RandomizeLayoutAttr>() &&
+        !Record->isUnion() && !getLangOpts().RandstructSeed.empty() &&
+        !Record->isRandomized()) {
+      SmallVector<Decl *, 32> OrigFieldOrdering(Record->fields());
+      SmallVector<Decl *, 32> NewFieldOrdering;
+      if (randstruct::randomizeStructureLayout(
+              Context, Record->getNameAsString(), OrigFieldOrdering,
+              NewFieldOrdering))
+        Record->reorderFields(NewFieldOrdering);
+    }
+
     // We may have deferred checking for a deleted destructor. Check now.
     if (CXXRecord) {
       auto *Dtor = CXXRecord->getDestructor();

clang/lib/Sema/SemaDeclAttr.cpp

@@ -5121,6 +5121,21 @@ static void handleLifetimeCategoryAttr(Sema &S, Decl *D, const ParsedAttr &AL) {
   }
 }
 
+static void handleRandomizeLayoutAttr(Sema &S, Decl *D, const ParsedAttr &AL) {
+  if (checkAttrMutualExclusion<NoRandomizeLayoutAttr>(S, D, AL))
+    return;
+  if (!D->hasAttr<RandomizeLayoutAttr>())
+    D->addAttr(::new (S.Context) RandomizeLayoutAttr(S.Context, AL));
+}
+
+static void handleNoRandomizeLayoutAttr(Sema &S, Decl *D,
+                                        const ParsedAttr &AL) {
+  if (checkAttrMutualExclusion<RandomizeLayoutAttr>(S, D, AL))
+    return;
+  if (!D->hasAttr<NoRandomizeLayoutAttr>())
+    D->addAttr(::new (S.Context) NoRandomizeLayoutAttr(S.Context, AL));
+}
+
 bool Sema::CheckCallingConvAttr(const ParsedAttr &Attrs, CallingConv &CC,
                                 const FunctionDecl *FD) {
   if (Attrs.isInvalid())
@@ -8635,6 +8650,12 @@ static void ProcessDeclAttribute(Sema &S, Scope *scope, Decl *D,
   case ParsedAttr::AT_Section:
     handleSectionAttr(S, D, AL);
     break;
+  case ParsedAttr::AT_RandomizeLayout:
+    handleRandomizeLayoutAttr(S, D, AL);
+    break;
+  case ParsedAttr::AT_NoRandomizeLayout:
+    handleNoRandomizeLayoutAttr(S, D, AL);
+    break;
   case ParsedAttr::AT_CodeSeg:
     handleCodeSegAttr(S, D, AL);
     break;

clang/test/Misc/pragma-attribute-supported-attributes-list.test

@@ -104,6 +104,7 @@
 // CHECK-NEXT: NoMicroMips (SubjectMatchRule_function)
 // CHECK-NEXT: NoMips16 (SubjectMatchRule_function)
 // CHECK-NEXT: NoProfileFunction (SubjectMatchRule_function)
+// CHECK-NEXT: NoRandomizeLayout (SubjectMatchRule_record)
 // CHECK-NEXT: NoSanitize (SubjectMatchRule_function, SubjectMatchRule_objc_method, SubjectMatchRule_variable_is_global)
 // CHECK-NEXT: NoSanitizeSpecific (SubjectMatchRule_function, SubjectMatchRule_variable_is_global)
 // CHECK-NEXT: NoSpeculativeLoadHardening (SubjectMatchRule_function, SubjectMatchRule_objc_method)
@@ -148,6 +149,7 @@
 // CHECK-NEXT: PassObjectSize (SubjectMatchRule_variable_is_parameter)
 // CHECK-NEXT: PatchableFunctionEntry (SubjectMatchRule_function, SubjectMatchRule_objc_method)
 // CHECK-NEXT: Pointer (SubjectMatchRule_record_not_is_union)
+// CHECK-NEXT: RandomizeLayout (SubjectMatchRule_record)
 // CHECK-NEXT: ReleaseHandle (SubjectMatchRule_variable_is_parameter)
 // CHECK-NEXT: RenderScriptKernel (SubjectMatchRule_function)
 // CHECK-NEXT: ReqdWorkGroupSize (SubjectMatchRule_function)

clang/unittests/AST/CMakeLists.txt

@@ -25,6 +25,7 @@ add_clang_unittest(ASTTests
   EvaluateAsRValueTest.cpp
   ExternalASTSourceTest.cpp
   NamedDeclPrinterTest.cpp
+  RandstructTest.cpp
   RecursiveASTVisitorTest.cpp
   SizelessTypesTest.cpp
   SourceLocationTest.cpp

clang/unittests/AST/RandstructTest.cpp

@@ -0,0 +1,424 @@
+//===- unittest/AST/RandstructTest.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 file contains tests for Clang's structure field layout randomization.
+//
+//===----------------------------------------------------------------------===//
+
+/*
+ * Build this test suite by running `make ASTTests` in the build folder.
+ *
+ * Run this test suite by running the following in the build folder:
+ * ` ./tools/clang/unittests/AST/ASTTests
+ * --gtest_filter=StructureLayoutRandomization*`
+ */
+
+#include "clang/AST/Randstruct.h"
+#include "gtest/gtest.h"
+
+#include "DeclMatcher.h"
+#include "clang/AST/RecordLayout.h"
+#include "clang/ASTMatchers/ASTMatchers.h"
+#include "clang/Frontend/ASTUnit.h"
+#include "clang/Testing/CommandLineArgs.h"
+#include "clang/Tooling/Tooling.h"
+
+#include <vector>
+
+using namespace clang;
+using namespace clang::ast_matchers;
+using namespace clang::randstruct;
+
+using field_names = std::vector<std::string>;
+
+namespace {
+
+std::unique_ptr<ASTUnit> makeAST(const std::string &SourceCode) {
+  std::vector<std::string> Args = getCommandLineArgsForTesting(Lang_C99);
+  Args.push_back("-frandomize-layout-seed=1234567890abcdef");
+
+  IgnoringDiagConsumer IgnoringConsumer = IgnoringDiagConsumer();
+
+  return tooling::buildASTFromCodeWithArgs(
+      SourceCode, Args, "input.c", "clang-tool",
+      std::make_shared<PCHContainerOperations>(),
+      tooling::getClangStripDependencyFileAdjuster(),
+      tooling::FileContentMappings(), &IgnoringConsumer);
+}
+
+RecordDecl *getRecordDeclFromAST(const ASTContext &C, const std::string &Name) {
+  RecordDecl *RD = FirstDeclMatcher<RecordDecl>().match(
+      C.getTranslationUnitDecl(), recordDecl(hasName(Name)));
+  return RD;
+}
+
+std::vector<std::string> getFieldNamesFromRecord(const RecordDecl *RD) {
+  std::vector<std::string> Fields;
+
+  Fields.reserve(8);
+  for (auto *Field : RD->fields())
+    Fields.push_back(Field->getNameAsString());
+
+  return Fields;
+}
+
+bool isSubsequence(const field_names &Seq, const field_names &Subseq) {
+  unsigned SeqLen = Seq.size();
+  unsigned SubLen = Subseq.size();
+
+  bool IsSubseq = false;
+  for (unsigned I = 0; I < SeqLen; ++I)
+    if (Seq[I] == Subseq[0]) {
+      IsSubseq = true;
+      for (unsigned J = 0; J + I < SeqLen && J < SubLen; ++J) {
+        if (Seq[J + I] != Subseq[J]) {
+          IsSubseq = false;
+          break;
+        }
+      }
+    }
+
+  return IsSubseq;
+}
+
+} // end anonymous namespace
+
+namespace clang {
+namespace ast_matchers {
+
+#define RANDSTRUCT_TEST_SUITE_TEST StructureLayoutRandomizationTestSuiteTest
+
+TEST(RANDSTRUCT_TEST_SUITE_TEST, CanDetermineIfSubsequenceExists) {
+  const field_names Seq = {"a", "b", "c", "d"};
+
+  EXPECT_TRUE(isSubsequence(Seq, {"b", "c"}));
+  EXPECT_TRUE(isSubsequence(Seq, {"a", "b", "c", "d"}));
+  EXPECT_TRUE(isSubsequence(Seq, {"b", "c", "d"}));
+  EXPECT_TRUE(isSubsequence(Seq, {"a"}));
+  EXPECT_FALSE(isSubsequence(Seq, {"a", "d"}));
+}
+
+#define RANDSTRUCT_TEST StructureLayoutRandomization
+
+TEST(RANDSTRUCT_TEST, UnmarkedStruct) {
+  const std::unique_ptr<ASTUnit> AST = makeAST(R"c(
+    struct test {
+        int bacon;
+        long lettuce;
+        long long tomato;
+        float mayonnaise;
+    };
+  )c");
+
+  EXPECT_FALSE(AST->getDiagnostics().hasErrorOccurred());
+
+  const RecordDecl *RD = getRecordDeclFromAST(AST->getASTContext(), "test");
+
+  EXPECT_FALSE(RD->hasAttr<RandomizeLayoutAttr>());
+  EXPECT_FALSE(RD->isRandomized());
+}
+
+TEST(RANDSTRUCT_TEST, MarkedNoRandomize) {
+  const std::unique_ptr<ASTUnit> AST = makeAST(R"c(
+    struct test {
+        int bacon;
+        long lettuce;
+        long long tomato;
+        float mayonnaise;
+    } __attribute__((no_randomize_layout));
+  )c");
+
+  EXPECT_FALSE(AST->getDiagnostics().hasErrorOccurred());
+
+  const RecordDecl *RD = getRecordDeclFromAST(AST->getASTContext(), "test");
+
+  EXPECT_TRUE(RD->hasAttr<NoRandomizeLayoutAttr>());
+  EXPECT_FALSE(RD->isRandomized());
+}
+
+TEST(RANDSTRUCT_TEST, MarkedRandomize) {
+  const std::unique_ptr<ASTUnit> AST = makeAST(R"c(
+    struct test {
+        int bacon;
+        long lettuce;
+        long long tomato;
+        float mayonnaise;
+    } __attribute__((randomize_layout));
+  )c");
+
+  EXPECT_FALSE(AST->getDiagnostics().hasErrorOccurred());
+
+  const RecordDecl *RD = getRecordDeclFromAST(AST->getASTContext(), "test");
+
+  EXPECT_TRUE(RD->hasAttr<RandomizeLayoutAttr>());
+  EXPECT_TRUE(RD->isRandomized());
+}
+
+TEST(RANDSTRUCT_TEST, MismatchedAttrsDeclVsDef) {
+  const std::unique_ptr<ASTUnit> AST = makeAST(R"c(
+    struct test __attribute__((randomize_layout));
+    struct test {
+        int bacon;
+        long lettuce;
+        long long tomato;
+        float mayonnaise;
+    } __attribute__((no_randomize_layout));
+  )c");
+
+  EXPECT_FALSE(AST->getDiagnostics().hasErrorOccurred());
+
+  DiagnosticsEngine &Diags = AST->getDiagnostics();
+
+  EXPECT_FALSE(Diags.hasFatalErrorOccurred());
+  EXPECT_FALSE(Diags.hasUncompilableErrorOccurred());
+  EXPECT_FALSE(Diags.hasUnrecoverableErrorOccurred());
+  EXPECT_EQ(Diags.getNumWarnings(), 1u);
+  EXPECT_EQ(Diags.getNumErrors(), 0u);
+}
+
+TEST(RANDSTRUCT_TEST, MismatchedAttrsRandomizeVsNoRandomize) {
+  const std::unique_ptr<ASTUnit> AST = makeAST(R"c(
+    struct test2 {
+        int bacon;
+        long lettuce;
+        long long tomato;
+        float mayonnaise;
+    } __attribute__((randomize_layout)) __attribute__((no_randomize_layout));
+  )c");
+
+  EXPECT_TRUE(AST->getDiagnostics().hasErrorOccurred());
+
+  DiagnosticsEngine &Diags = AST->getDiagnostics();
+
+  EXPECT_TRUE(Diags.hasUncompilableErrorOccurred());
+  EXPECT_TRUE(Diags.hasUnrecoverableErrorOccurred());
+  EXPECT_EQ(Diags.getNumWarnings(), 0u);
+  EXPECT_EQ(Diags.getNumErrors(), 1u);
+}
+
+TEST(RANDSTRUCT_TEST, MismatchedAttrsNoRandomizeVsRandomize) {
+  const std::unique_ptr<ASTUnit> AST = makeAST(R"c(
+    struct test3 {
+        int bacon;
+        long lettuce;
+        long long tomato;
+        float mayonnaise;
+    } __attribute__((no_randomize_layout)) __attribute__((randomize_layout));
+  )c");
+
+  EXPECT_TRUE(AST->getDiagnostics().hasErrorOccurred());
+
+  DiagnosticsEngine &Diags = AST->getDiagnostics();
+
+  EXPECT_TRUE(Diags.hasUncompilableErrorOccurred());
+  EXPECT_TRUE(Diags.hasUnrecoverableErrorOccurred());
+  EXPECT_EQ(Diags.getNumWarnings(), 0u);
+  EXPECT_EQ(Diags.getNumErrors(), 1u);
+}
+
+TEST(RANDSTRUCT_TEST, CheckAdjacentBitfieldsRemainAdjacentAfterRandomization) {
+  const std::unique_ptr<ASTUnit> AST = makeAST(R"c(
+    struct test {
+        int a;
+        int b;
+        int x : 1;
+        int y : 1;
+        int z : 1;
+        int c;
+    } __attribute__((randomize_layout));
+  )c");
+
+  EXPECT_FALSE(AST->getDiagnostics().hasErrorOccurred());
+
+  const RecordDecl *RD = getRecordDeclFromAST(AST->getASTContext(), "test");
+  const field_names Actual = getFieldNamesFromRecord(RD);
+  const field_names Subseq = {"x", "y", "z"};
+
+  EXPECT_TRUE(RD->isRandomized());
+  EXPECT_TRUE(isSubsequence(Actual, Subseq));
+}
+
+TEST(RANDSTRUCT_TEST, CheckVariableLengthArrayMemberRemainsAtEndOfStructure) {
+  const std::unique_ptr<ASTUnit> AST = makeAST(R"c(
+    struct test {
+        int a;
+        double b;
+        short c;
+        char name[];
+    } __attribute__((randomize_layout));
+  )c");
+
+  EXPECT_FALSE(AST->getDiagnostics().hasErrorOccurred());
+
+  const RecordDecl *RD = getRecordDeclFromAST(AST->getASTContext(), "test");
+
+  EXPECT_TRUE(RD->isRandomized());
+}
+
+TEST(RANDSTRUCT_TEST, RandstructDoesNotOverrideThePackedAttr) {
+  const std::unique_ptr<ASTUnit> AST = makeAST(R"c(
+    struct test_struct {
+        char a;
+        float b[3];
+        short c;
+        int d;
+    } __attribute__((packed, randomize_layout));
+
+    struct another_struct {
+        char a;
+        char b[5];
+        int c;
+    } __attribute__((packed, randomize_layout));
+
+    struct last_struct {
+        char a;
+        long long b;
+        int c[];
+    } __attribute__((packed, randomize_layout));
+  )c");
+
+  EXPECT_FALSE(AST->getDiagnostics().hasErrorOccurred());
+
+  // FIXME (?): calling getASTRecordLayout is probably a necessary evil so that
+  // Clang's RecordBuilders can actually flesh out the information like
+  // alignment, etc.
+  {
+    const RecordDecl *RD =
+        getRecordDeclFromAST(AST->getASTContext(), "test_struct");
+    const ASTRecordLayout *Layout =
+        &AST->getASTContext().getASTRecordLayout(RD);
+
+    EXPECT_TRUE(RD->isRandomized());
+    EXPECT_EQ(19, Layout->getSize().getQuantity());
+  }
+
+  {
+    const RecordDecl *RD =
+        getRecordDeclFromAST(AST->getASTContext(), "another_struct");
+    const ASTRecordLayout *Layout =
+        &AST->getASTContext().getASTRecordLayout(RD);
+
+    EXPECT_TRUE(RD->isRandomized());
+    EXPECT_EQ(10, Layout->getSize().getQuantity());
+  }
+
+  {
+    const RecordDecl *RD =
+        getRecordDeclFromAST(AST->getASTContext(), "last_struct");
+    const ASTRecordLayout *Layout =
+        &AST->getASTContext().getASTRecordLayout(RD);
+
+    EXPECT_TRUE(RD->isRandomized());
+    EXPECT_EQ(9, Layout->getSize().getQuantity());
+  }
+}
+
+TEST(RANDSTRUCT_TEST, ZeroWidthBitfieldsSeparateAllocationUnits) {
+  const std::unique_ptr<ASTUnit> AST = makeAST(R"c(
+    struct test {
+        int a : 1;
+        int   : 0;
+        int b : 1;
+    } __attribute__((randomize_layout));
+  )c");
+
+  EXPECT_FALSE(AST->getDiagnostics().hasErrorOccurred());
+
+  const RecordDecl *RD = getRecordDeclFromAST(AST->getASTContext(), "test");
+
+  EXPECT_TRUE(RD->isRandomized());
+}
+
+TEST(RANDSTRUCT_TEST, RandstructDoesNotRandomizeUnionFieldOrder) {
+  const std::unique_ptr<ASTUnit> AST = makeAST(R"c(
+    union test_union {
+        int a;
+        int b;
+        int c;
+        int d;
+        int e;
+        int f;
+    } __attribute__((randomize_layout));
+  )c");
+
+  EXPECT_FALSE(AST->getDiagnostics().hasErrorOccurred());
+
+  const RecordDecl *RD =
+      getRecordDeclFromAST(AST->getASTContext(), "test_union");
+
+  EXPECT_FALSE(RD->isRandomized());
+}
+
+TEST(RANDSTRUCT_TEST, AnonymousStructsAndUnionsRetainFieldOrder) {
+  const std::unique_ptr<ASTUnit> AST = makeAST(R"c(
+    struct test_struct {
+        int a;
+        struct sub_struct {
+            int b;
+            int c;
+            int d;
+            int e;
+            int f;
+        } __attribute__((randomize_layout)) s;
+        int f;
+        struct {
+            int g;
+            int h;
+            int i;
+            int j;
+            int k;
+        };
+        int l;
+        union {
+            int m;
+            int n;
+            int o;
+            int p;
+            int q;
+        };
+        int r;
+    } __attribute__((randomize_layout));
+  )c");
+
+  EXPECT_FALSE(AST->getDiagnostics().hasErrorOccurred());
+
+  const RecordDecl *RD =
+      getRecordDeclFromAST(AST->getASTContext(), "test_struct");
+
+  EXPECT_TRUE(RD->isRandomized());
+
+  bool AnonStructTested = false;
+  bool AnonUnionTested = false;
+
+  for (const Decl *D : RD->decls())
+    if (const FieldDecl *FD = dyn_cast<FieldDecl>(D)) {
+      if (const auto *Record = FD->getType()->getAs<RecordType>()) {
+        RD = Record->getDecl();
+        if (RD->isAnonymousStructOrUnion()) {
+          // These field orders shouldn't change.
+          if (RD->isUnion()) {
+            const field_names Expected = {"m", "n", "o", "p", "q"};
+
+            EXPECT_EQ(Expected, getFieldNamesFromRecord(RD));
+            AnonUnionTested = true;
+          } else {
+            const field_names Expected = {"g", "h", "i", "j", "k"};
+
+            EXPECT_EQ(Expected, getFieldNamesFromRecord(RD));
+            AnonStructTested = true;
+          }
+        }
+      }
+    }
+
+  EXPECT_TRUE(AnonStructTested);
+  EXPECT_TRUE(AnonUnionTested);
+}
+
+} // namespace ast_matchers
+} // namespace clang