Merge branch 'main' into remove_dead_availability_annotations

Author: ldionne

bolt/include/bolt/Core/BinaryFunction.h

@@ -804,6 +804,19 @@ class BinaryFunction {
     return iterator_range<const_cfi_iterator>(cie_begin(), cie_end());
   }
 
+  /// Iterate over instructions (only if CFG is unavailable or not built yet).
+  iterator_range<InstrMapType::iterator> instrs() {
+    assert(!hasCFG() && "Iterate over basic blocks instead");
+    return make_range(Instructions.begin(), Instructions.end());
+  }
+  iterator_range<InstrMapType::const_iterator> instrs() const {
+    assert(!hasCFG() && "Iterate over basic blocks instead");
+    return make_range(Instructions.begin(), Instructions.end());
+  }
+
+  /// Returns whether there are any labels at Offset.
+  bool hasLabelAt(unsigned Offset) const { return Labels.count(Offset) != 0; }
+
   /// Iterate over all jump tables associated with this function.
   iterator_range<std::map<uint64_t, JumpTable *>::const_iterator>
   jumpTables() const {

bolt/include/bolt/Core/MCPlusBuilder.h

@@ -49,6 +49,7 @@ class MCSymbol;
 class raw_ostream;
 
 namespace bolt {
+class BinaryBasicBlock;
 class BinaryFunction;
 
 /// Different types of indirect branches encountered during disassembly.
@@ -572,6 +573,11 @@ class MCPlusBuilder {
     return false;
   }
 
+  virtual MCPhysReg getSignedReg(const MCInst &Inst) const {
+    llvm_unreachable("not implemented");
+    return getNoRegister();
+  }
+
   virtual ErrorOr<MCPhysReg> getRegUsedAsRetDest(const MCInst &Inst) const {
     llvm_unreachable("not implemented");
     return getNoRegister();
@@ -622,6 +628,54 @@ class MCPlusBuilder {
     return std::make_pair(getNoRegister(), getNoRegister());
   }
 
+  /// Analyzes if a pointer is checked to be authenticated successfully
+  /// by the end of the basic block.
+  ///
+  /// It is possible for pointer authentication instructions not to terminate
+  /// the program abnormally on authentication failure and return some invalid
+  /// pointer instead (like it is done on AArch64 when FEAT_FPAC is not
+  /// implemented). This might be enough to crash on invalid memory access when
+  /// the pointer is later used as the destination of a load, store, or branch
+  /// instruction. On the other hand, when the pointer is not used right away,
+  /// it may be important for the compiler to check the address explicitly not
+  /// to introduce a signing or authentication oracle.
+  ///
+  /// This function is intended to detect a complex, multi-instruction pointer-
+  /// checking sequence spanning a contiguous range of instructions at the end
+  /// of the basic block (as these sequences are expected to end with a
+  /// conditional branch - this is how they are implemented on AArch64 by LLVM).
+  /// If a (Reg, FirstInst) pair is returned and before execution of FirstInst
+  /// Reg was last written to by an authentication instruction, then it is known
+  /// that in any successor of BB either
+  /// * the authentication instruction that last wrote to Reg succeeded, or
+  /// * the program is terminated abnormally without introducing any signing
+  ///   or authentication oracles
+  ///
+  /// Note that this function is not expected to repeat the results returned
+  /// by getAuthCheckedReg(Inst, MayOverwrite) function below.
+  virtual std::optional<std::pair<MCPhysReg, MCInst *>>
+  getAuthCheckedReg(BinaryBasicBlock &BB) const {
+    llvm_unreachable("not implemented");
+    return std::nullopt;
+  }
+
+  /// Returns the register that is checked to be authenticated successfully.
+  ///
+  /// If the returned register was last written to by an authentication
+  /// instruction and that authentication failed, then the program is known
+  /// to be terminated abnormally as a result of execution of Inst.
+  ///
+  /// Additionally, if MayOverwrite is false, it is known that the authenticated
+  /// pointer is not clobbered by Inst itself.
+  ///
+  /// Use this function for simple, single-instruction patterns instead of
+  /// its getAuthCheckedReg(BB) counterpart.
+  virtual MCPhysReg getAuthCheckedReg(const MCInst &Inst,
+                                      bool MayOverwrite) const {
+    llvm_unreachable("not implemented");
+    return getNoRegister();
+  }
+
   virtual bool isTerminator(const MCInst &Inst) const;
 
   virtual bool isNoop(const MCInst &Inst) const {

bolt/include/bolt/Passes/PAuthGadgetScanner.h

@@ -12,7 +12,6 @@
 #include "bolt/Core/BinaryContext.h"
 #include "bolt/Core/BinaryFunction.h"
 #include "bolt/Passes/BinaryPasses.h"
-#include "llvm/ADT/SmallSet.h"
 #include "llvm/Support/raw_ostream.h"
 #include <memory>
 
@@ -65,6 +64,14 @@ struct MCInstInBFReference {
   uint64_t Offset;
   MCInstInBFReference(BinaryFunction *BF, uint64_t Offset)
       : BF(BF), Offset(Offset) {}
+
+  static MCInstInBFReference get(const MCInst *Inst, BinaryFunction &BF) {
+    for (auto &I : BF.instrs())
+      if (Inst == &I.second)
+        return MCInstInBFReference(&BF, I.first);
+    return {};
+  }
+
   MCInstInBFReference() : BF(nullptr), Offset(0) {}
   bool operator==(const MCInstInBFReference &RHS) const {
     return BF == RHS.BF && Offset == RHS.Offset;
@@ -104,6 +111,12 @@ struct MCInstReference {
   MCInstReference(BinaryFunction *BF, uint32_t Offset)
       : MCInstReference(MCInstInBFReference(BF, Offset)) {}
 
+  static MCInstReference get(const MCInst *Inst, BinaryFunction &BF) {
+    if (BF.hasCFG())
+      return MCInstInBBReference::get(Inst, BF);
+    return MCInstInBFReference::get(Inst, BF);
+  }
+
   bool operator<(const MCInstReference &RHS) const {
     if (ParentKind != RHS.ParentKind)
       return ParentKind < RHS.ParentKind;
@@ -138,6 +151,16 @@ struct MCInstReference {
     llvm_unreachable("");
   }
 
+  operator bool() const {
+    switch (ParentKind) {
+    case BasicBlockParent:
+      return U.BBRef.BB != nullptr;
+    case FunctionParent:
+      return U.BFRef.BF != nullptr;
+    }
+    llvm_unreachable("");
+  }
+
   uint64_t getAddress() const {
     switch (ParentKind) {
     case BasicBlockParent:
@@ -173,9 +196,6 @@ raw_ostream &operator<<(raw_ostream &OS, const MCInstReference &);
 
 namespace PAuthGadgetScanner {
 
-class SrcSafetyAnalysis;
-struct SrcState;
-
 /// Description of a gadget kind that can be detected. Intended to be
 /// statically allocated to be attached to reports by reference.
 class GadgetKind {
@@ -184,7 +204,7 @@ class GadgetKind {
 public:
   GadgetKind(const char *Description) : Description(Description) {}
 
-  const StringRef getDescription() const { return Description; }
+  StringRef getDescription() const { return Description; }
 };
 
 /// Base report located at some instruction, without any additional information.
@@ -199,8 +219,8 @@ struct Report {
 
   // The two methods below are called by Analysis::computeDetailedInfo when
   // iterating over the reports.
-  virtual const ArrayRef<MCPhysReg> getAffectedRegisters() const { return {}; }
-  virtual void setOverwritingInstrs(const ArrayRef<MCInstReference> Instrs) {}
+  virtual ArrayRef<MCPhysReg> getAffectedRegisters() const { return {}; }
+  virtual void setOverwritingInstrs(ArrayRef<MCInstReference> Instrs) {}
 
   void printBasicInfo(raw_ostream &OS, const BinaryContext &BC,
                       StringRef IssueKind) const;
@@ -223,19 +243,19 @@ struct GadgetReport : public Report {
 
   void generateReport(raw_ostream &OS, const BinaryContext &BC) const override;
 
-  const ArrayRef<MCPhysReg> getAffectedRegisters() const override {
+  ArrayRef<MCPhysReg> getAffectedRegisters() const override {
     return AffectedRegisters;
   }
 
-  void setOverwritingInstrs(const ArrayRef<MCInstReference> Instrs) override {
+  void setOverwritingInstrs(ArrayRef<MCInstReference> Instrs) override {
     OverwritingInstrs.assign(Instrs.begin(), Instrs.end());
   }
 };
 
 /// Report with a free-form message attached.
 struct GenericReport : public Report {
   std::string Text;
-  GenericReport(MCInstReference Location, const std::string &Text)
+  GenericReport(MCInstReference Location, StringRef Text)
       : Report(Location), Text(Text) {}
   virtual void generateReport(raw_ostream &OS,
                               const BinaryContext &BC) const override;

bolt/include/bolt/Profile/DataReader.h

@@ -114,10 +114,8 @@ struct FuncBranchData {
 
   FuncBranchData() {}
 
-  FuncBranchData(StringRef Name, ContainerTy Data)
-      : Name(Name), Data(std::move(Data)) {}
-
-  FuncBranchData(StringRef Name, ContainerTy Data, ContainerTy EntryData)
+  FuncBranchData(StringRef Name, ContainerTy Data = ContainerTy(),
+                 ContainerTy EntryData = ContainerTy())
       : Name(Name), Data(std::move(Data)), EntryData(std::move(EntryData)) {}
 
   ErrorOr<const BranchInfo &> getBranch(uint64_t From, uint64_t To) const;
@@ -205,7 +203,7 @@ struct FuncMemData {
 
   FuncMemData() {}
 
-  FuncMemData(StringRef Name, ContainerTy Data)
+  FuncMemData(StringRef Name, ContainerTy Data = ContainerTy())
       : Name(Name), Data(std::move(Data)) {}
 };
 
@@ -241,7 +239,7 @@ struct FuncBasicSampleData {
   StringRef Name;
   ContainerTy Data;
 
-  FuncBasicSampleData(StringRef Name, ContainerTy Data)
+  FuncBasicSampleData(StringRef Name, ContainerTy Data = ContainerTy())
       : Name(Name), Data(std::move(Data)) {}
 
   /// Get the number of samples recorded in [Start, End)

bolt/lib/Core/BinaryFunction.cpp

@@ -1783,10 +1783,22 @@ bool BinaryFunction::scanExternalRefs() {
     // On AArch64, we use instruction patches for fixing references. We make an
     // exception for branch instructions since they require optional
     // relocations.
-    if (BC.isAArch64() && !BranchTargetSymbol) {
-      LLVM_DEBUG(BC.printInstruction(dbgs(), Instruction, AbsoluteInstrAddr));
-      InstructionPatches.push_back({AbsoluteInstrAddr, Instruction});
-      continue;
+    if (BC.isAArch64()) {
+      if (!BranchTargetSymbol) {
+        LLVM_DEBUG(BC.printInstruction(dbgs(), Instruction, AbsoluteInstrAddr));
+        InstructionPatches.push_back({AbsoluteInstrAddr, Instruction});
+        continue;
+      }
+
+      // Conditional tail calls require new relocation types that are currently
+      // not supported. https://github.com/llvm/llvm-project/issues/138264
+      if (BC.MIB->isConditionalBranch(Instruction)) {
+        if (BinaryFunction *TargetBF =
+                BC.getFunctionForSymbol(BranchTargetSymbol)) {
+          TargetBF->setNeedsPatch(true);
+          continue;
+        }
+      }
     }
 
     // Emit the instruction using temp emitter and generate relocations.
@@ -3326,7 +3338,7 @@ void BinaryFunction::duplicateConstantIslands() {
 static std::string constructFilename(std::string Filename,
                                      std::string Annotation,
                                      std::string Suffix) {
-  std::replace(Filename.begin(), Filename.end(), '/', '-');
+  llvm::replace(Filename, '/', '-');
   if (!Annotation.empty())
     Annotation.insert(0, "-");
   if (Filename.size() + Annotation.size() + Suffix.size() > MAX_PATH) {

bolt/lib/Core/DebugData.cpp

@@ -676,7 +676,6 @@ static void writeDWARF5LocList(uint32_t &NumberOfEntries, DIEValue &AttrInfo,
     return;
   }
 
-  std::vector<uint64_t> OffsetsArray;
   auto writeExpression = [&](uint32_t Index) -> void {
     const DebugLocationEntry &Entry = LocList[Index];
     encodeULEB128(Entry.Expr.size(), LocBodyStream);

bolt/lib/Passes/AsmDump.cpp

@@ -109,7 +109,7 @@ void dumpFunction(const BinaryFunction &BF) {
   }
 
   std::string PrintName = BF.getPrintName();
-  std::replace(PrintName.begin(), PrintName.end(), '/', '-');
+  llvm::replace(PrintName, '/', '-');
   std::string Filename =
       opts::AsmDump.empty()
           ? (PrintName + ".s")

bolt/lib/Passes/BinaryPasses.cpp

@@ -35,7 +35,7 @@ static const char *dynoStatsOptName(const bolt::DynoStats::Category C) {
 
   OptNames[C] = bolt::DynoStats::Description(C);
 
-  std::replace(OptNames[C].begin(), OptNames[C].end(), ' ', '-');
+  llvm::replace(OptNames[C], ' ', '-');
 
   return OptNames[C].c_str();
 }

bolt/lib/Passes/FrameAnalysis.cpp

@@ -320,7 +320,6 @@ bool FrameAnalysis::updateArgsTouchedFor(const BinaryFunction &BF, MCInst &Inst,
   if (!BC.MIB->isCall(Inst))
     return false;
 
-  std::set<int64_t> Res;
   const MCSymbol *TargetSymbol = BC.MIB->getTargetSymbol(Inst);
   // If indirect call, we conservatively assume it accesses all stack positions
   if (TargetSymbol == nullptr) {

bolt/lib/Passes/HFSort.cpp

@@ -239,7 +239,6 @@ std::vector<Cluster> clusterize(const CallGraph &Cg) {
 }
 
 std::vector<Cluster> randomClusters(const CallGraph &Cg) {
-  std::vector<NodeId> FuncIds(Cg.numNodes(), 0);
   std::vector<Cluster> Clusters;
   Clusters.reserve(Cg.numNodes());