Merge branch 'main' into clang_second_arg_is_last

Author: imdj

bolt/include/bolt/Core/BinaryContext.h

@@ -1295,7 +1295,7 @@ class BinaryContext {
   void foldFunction(BinaryFunction &ChildBF, BinaryFunction &ParentBF);
 
   /// Add a Section relocation at a given \p Address.
-  void addRelocation(uint64_t Address, MCSymbol *Symbol, uint64_t Type,
+  void addRelocation(uint64_t Address, MCSymbol *Symbol, uint32_t Type,
                      uint64_t Addend = 0, uint64_t Value = 0);
 
   /// Return a relocation registered at a given \p Address, or nullptr if there
@@ -1308,7 +1308,7 @@ class BinaryContext {
   }
 
   /// Register dynamic relocation at \p Address.
-  void addDynamicRelocation(uint64_t Address, MCSymbol *Symbol, uint64_t Type,
+  void addDynamicRelocation(uint64_t Address, MCSymbol *Symbol, uint32_t Type,
                             uint64_t Addend, uint64_t Value = 0);
 
   /// Return a dynamic relocation registered at a given \p Address, or nullptr

bolt/include/bolt/Core/BinaryFunction.h

@@ -1260,7 +1260,7 @@ class BinaryFunction {
   /// Register relocation type \p RelType at a given \p Address in the function
   /// against \p Symbol.
   /// Assert if the \p Address is not inside this function.
-  void addRelocation(uint64_t Address, MCSymbol *Symbol, uint64_t RelType,
+  void addRelocation(uint64_t Address, MCSymbol *Symbol, uint32_t RelType,
                      uint64_t Addend, uint64_t Value);
 
   /// Return the name of the section this function originated from.

bolt/include/bolt/Core/BinarySection.h

@@ -358,14 +358,14 @@ class BinarySection {
   void clearRelocations();
 
   /// Add a new relocation at the given /p Offset.
-  void addRelocation(uint64_t Offset, MCSymbol *Symbol, uint64_t Type,
+  void addRelocation(uint64_t Offset, MCSymbol *Symbol, uint32_t Type,
                      uint64_t Addend, uint64_t Value = 0) {
     assert(Offset < getSize() && "offset not within section bounds");
     Relocations.emplace(Relocation{Offset, Symbol, Type, Addend, Value});
   }
 
   /// Add a dynamic relocation at the given /p Offset.
-  void addDynamicRelocation(uint64_t Offset, MCSymbol *Symbol, uint64_t Type,
+  void addDynamicRelocation(uint64_t Offset, MCSymbol *Symbol, uint32_t Type,
                             uint64_t Addend, uint64_t Value = 0) {
     addDynamicRelocation(Relocation{Offset, Symbol, Type, Addend, Value});
   }

bolt/include/bolt/Core/MCPlusBuilder.h

@@ -473,7 +473,7 @@ class MCPlusBuilder {
   ///
   /// For X86, they might be used in scanExternalRefs when we want to skip
   /// a function but still patch references inside it.
-  virtual bool shouldRecordCodeRelocation(uint64_t RelType) const {
+  virtual bool shouldRecordCodeRelocation(uint32_t RelType) const {
     llvm_unreachable("not implemented");
     return false;
   }
@@ -637,6 +637,16 @@ class MCPlusBuilder {
     return false;
   }
 
+  virtual bool isAddXri(const MCInst &Inst) const {
+    llvm_unreachable("not implemented");
+    return false;
+  }
+
+  virtual bool isMOVW(const MCInst &Inst) const {
+    llvm_unreachable("not implemented");
+    return false;
+  }
+
   virtual bool isMoveMem2Reg(const MCInst &Inst) const { return false; }
 
   virtual bool mayLoad(const MCInst &Inst) const {
@@ -1074,15 +1084,15 @@ class MCPlusBuilder {
   /// MCExpr referencing \p Symbol + \p Addend.
   virtual bool setOperandToSymbolRef(MCInst &Inst, int OpNum,
                                      const MCSymbol *Symbol, int64_t Addend,
-                                     MCContext *Ctx, uint64_t RelType) const;
+                                     MCContext *Ctx, uint32_t RelType) const;
 
   /// Replace an immediate operand in the instruction \p Inst with a reference
   /// of the passed \p Symbol plus \p Addend. If the instruction does not have
   /// an immediate operand or has more than one - then return false. Otherwise
   /// return true.
   virtual bool replaceImmWithSymbolRef(MCInst &Inst, const MCSymbol *Symbol,
                                        int64_t Addend, MCContext *Ctx,
-                                       int64_t &Value, uint64_t RelType) const {
+                                       int64_t &Value, uint32_t RelType) const {
     llvm_unreachable("not implemented");
     return false;
   }
@@ -1287,7 +1297,7 @@ class MCPlusBuilder {
   /// Return the MCExpr used for absolute references in this target
   virtual const MCExpr *getTargetExprFor(MCInst &Inst, const MCExpr *Expr,
                                          MCContext &Ctx,
-                                         uint64_t RelType) const {
+                                         uint32_t RelType) const {
     return Expr;
   }
 

bolt/include/bolt/Core/Relocation.h

@@ -20,6 +20,11 @@
 
 namespace llvm {
 class MCSymbol;
+
+namespace object {
+class RelocationRef;
+} // namespace object
+
 class raw_ostream;
 
 namespace ELF {
@@ -40,7 +45,7 @@ struct Relocation {
   MCSymbol *Symbol;
 
   /// Relocation type.
-  uint64_t Type;
+  uint32_t Type;
 
   /// The offset from the \p Symbol base used to compute the final
   /// value of this relocation.
@@ -51,71 +56,70 @@ struct Relocation {
   uint64_t Value;
 
   /// Return size in bytes of the given relocation \p Type.
-  static size_t getSizeForType(uint64_t Type);
+  static size_t getSizeForType(uint32_t Type);
 
   /// Return size of this relocation.
   size_t getSize() const { return getSizeForType(Type); }
 
   /// Skip relocations that we don't want to handle in BOLT
-  static bool skipRelocationType(uint64_t Type);
+  static bool skipRelocationType(uint32_t Type);
 
-  /// Handle special cases when relocation should not be processed by BOLT or
-  /// change relocation \p Type to proper one before continuing if \p Contents
-  /// and \P Type mismatch occurred.
-  static bool skipRelocationProcess(uint64_t &Type, uint64_t Contents);
-
-  // Adjust value depending on relocation type (make it PC relative or not)
-  static uint64_t encodeValue(uint64_t Type, uint64_t Value, uint64_t PC);
+  /// Adjust value depending on relocation type (make it PC relative or not).
+  static uint64_t encodeValue(uint32_t Type, uint64_t Value, uint64_t PC);
 
   /// Extract current relocated value from binary contents. This is used for
   /// RISC architectures where values are encoded in specific bits depending
   /// on the relocation value. For X86, we limit to sign extending the value
   /// if necessary.
-  static uint64_t extractValue(uint64_t Type, uint64_t Contents, uint64_t PC);
+  static uint64_t extractValue(uint32_t Type, uint64_t Contents, uint64_t PC);
 
   /// Return true if relocation type is PC-relative. Return false otherwise.
-  static bool isPCRelative(uint64_t Type);
+  static bool isPCRelative(uint32_t Type);
 
   /// Check if \p Type is a supported relocation type.
-  static bool isSupported(uint64_t Type);
+  static bool isSupported(uint32_t Type);
 
   /// Return true if relocation type implies the creation of a GOT entry
-  static bool isGOT(uint64_t Type);
+  static bool isGOT(uint32_t Type);
 
   /// Special relocation type that allows the linker to modify the instruction.
-  static bool isX86GOTPCRELX(uint64_t Type);
-  static bool isX86GOTPC64(uint64_t Type);
+  static bool isX86GOTPCRELX(uint32_t Type);
+  static bool isX86GOTPC64(uint32_t Type);
 
   /// Return true if relocation type is NONE
-  static bool isNone(uint64_t Type);
+  static bool isNone(uint32_t Type);
 
   /// Return true if relocation type is RELATIVE
-  static bool isRelative(uint64_t Type);
+  static bool isRelative(uint32_t Type);
 
   /// Return true if relocation type is IRELATIVE
-  static bool isIRelative(uint64_t Type);
+  static bool isIRelative(uint32_t Type);
 
   /// Return true if relocation type is for thread local storage.
-  static bool isTLS(uint64_t Type);
+  static bool isTLS(uint32_t Type);
 
   /// Return true of relocation type is for referencing a specific instruction
   /// (as opposed to a function, basic block, etc).
-  static bool isInstructionReference(uint64_t Type);
+  static bool isInstructionReference(uint32_t Type);
+
+  /// Return the relocation type of \p Rel from llvm::object. It checks for
+  /// overflows as BOLT uses 32 bits for the type.
+  static uint32_t getType(const object::RelocationRef &Rel);
 
   /// Return code for a NONE relocation
-  static uint64_t getNone();
+  static uint32_t getNone();
 
   /// Return code for a PC-relative 4-byte relocation
-  static uint64_t getPC32();
+  static uint32_t getPC32();
 
   /// Return code for a PC-relative 8-byte relocation
-  static uint64_t getPC64();
+  static uint32_t getPC64();
 
   /// Return code for a ABS 8-byte relocation
-  static uint64_t getAbs64();
+  static uint32_t getAbs64();
 
   /// Return code for a RELATIVE relocation
-  static uint64_t getRelative();
+  static uint32_t getRelative();
 
   /// Return true if this relocation is PC-relative. Return false otherwise.
   bool isPCRelative() const { return isPCRelative(Type); }
@@ -161,7 +165,7 @@ struct Relocation {
   const MCExpr *createExpr(MCStreamer *Streamer) const;
   const MCExpr *createExpr(MCStreamer *Streamer,
                            const MCExpr *RetainedValue) const;
-  static MCBinaryExpr::Opcode getComposeOpcodeFor(uint64_t Type);
+  static MCBinaryExpr::Opcode getComposeOpcodeFor(uint32_t Type);
 };
 
 /// Relocation ordering by offset.

bolt/include/bolt/Rewrite/RewriteInstance.h

@@ -248,7 +248,7 @@ class RewriteInstance {
   /// The \p SymbolName, \p SymbolAddress, \p Addend and \p ExtractedValue
   /// parameters will be set on success. The \p Skip argument indicates
   /// that the relocation was analyzed, but it must not be processed.
-  bool analyzeRelocation(const object::RelocationRef &Rel, uint64_t &RType,
+  bool analyzeRelocation(const object::RelocationRef &Rel, uint32_t &RType,
                          std::string &SymbolName, bool &IsSectionRelocation,
                          uint64_t &SymbolAddress, int64_t &Addend,
                          uint64_t &ExtractedValue, bool &Skip) const;

bolt/lib/Core/BinaryContext.cpp

@@ -2284,7 +2284,7 @@ ErrorOr<int64_t> BinaryContext::getSignedValueAtAddress(uint64_t Address,
 }
 
 void BinaryContext::addRelocation(uint64_t Address, MCSymbol *Symbol,
-                                  uint64_t Type, uint64_t Addend,
+                                  uint32_t Type, uint64_t Addend,
                                   uint64_t Value) {
   ErrorOr<BinarySection &> Section = getSectionForAddress(Address);
   assert(Section && "cannot find section for address");
@@ -2293,7 +2293,7 @@ void BinaryContext::addRelocation(uint64_t Address, MCSymbol *Symbol,
 }
 
 void BinaryContext::addDynamicRelocation(uint64_t Address, MCSymbol *Symbol,
-                                         uint64_t Type, uint64_t Addend,
+                                         uint32_t Type, uint64_t Addend,
                                          uint64_t Value) {
   ErrorOr<BinarySection &> Section = getSectionForAddress(Address);
   assert(Section && "cannot find section for address");

bolt/lib/Core/BinaryFunction.cpp

@@ -1473,10 +1473,19 @@ Error BinaryFunction::disassemble() {
           }
         }
 
+        uint64_t Addend = Relocation.Addend;
+
+        // For GOT relocations, create a reference against GOT entry ignoring
+        // the relocation symbol.
+        if (Relocation::isGOT(Relocation.Type)) {
+          assert(Relocation::isPCRelative(Relocation.Type) &&
+                 "GOT relocation must be PC-relative on RISC-V");
+          Symbol = BC.registerNameAtAddress("__BOLT_got_zero", 0, 0, 0);
+          Addend = Relocation.Value + Relocation.Offset + getAddress();
+        }
         int64_t Value = Relocation.Value;
         const bool Result = BC.MIB->replaceImmWithSymbolRef(
-            Instruction, Symbol, Relocation.Addend, Ctx.get(), Value,
-            Relocation.Type);
+            Instruction, Symbol, Addend, Ctx.get(), Value, Relocation.Type);
         (void)Result;
         assert(Result && "cannot replace immediate with relocation");
       }
@@ -4614,7 +4623,7 @@ bool BinaryFunction::isAArch64Veneer() const {
 }
 
 void BinaryFunction::addRelocation(uint64_t Address, MCSymbol *Symbol,
-                                   uint64_t RelType, uint64_t Addend,
+                                   uint32_t RelType, uint64_t Addend,
                                    uint64_t Value) {
   assert(Address >= getAddress() && Address < getAddress() + getMaxSize() &&
          "address is outside of the function");

bolt/lib/Core/JumpTable.cpp

@@ -84,7 +84,7 @@ void bolt::JumpTable::updateOriginal() {
   const uint64_t BaseOffset = getAddress() - getSection().getAddress();
   uint64_t EntryOffset = BaseOffset;
   for (MCSymbol *Entry : Entries) {
-    const uint64_t RelType =
+    const uint32_t RelType =
         Type == JTT_NORMAL ? ELF::R_X86_64_64 : ELF::R_X86_64_PC32;
     const uint64_t RelAddend =
         Type == JTT_NORMAL ? 0 : EntryOffset - BaseOffset;

bolt/lib/Core/MCPlusBuilder.cpp

@@ -551,7 +551,7 @@ void MCPlusBuilder::initSizeMap() {
 bool MCPlusBuilder::setOperandToSymbolRef(MCInst &Inst, int OpNum,
                                           const MCSymbol *Symbol,
                                           int64_t Addend, MCContext *Ctx,
-                                          uint64_t RelType) const {
+                                          uint32_t RelType) const {
   MCOperand Operand;
   if (!Addend) {
     Operand = MCOperand::createExpr(getTargetExprFor(