[llvm] use 64-bit types for result of getDwarfRegNum (NFC) (#109494)

The register encoding used by NVPTX and cuda-gdb basically use strings
encoded as numbers. They are always within 64-bits, but typically
outside of 32-bits, since they often need at least 5 characters.

This patch changes the signature of `MCRegisterInfo::getDwarfRegNum` and
some related data structures to use 64-bit numbers to accommodate
encodings like this.

Additionally, `MCRegisterInfo::getDwarfRegNum` is marked as virtual, so
that targets with peculiar dwarf register mapping schemes (such as
NVPTX) can override its behavior.

I originally tried to do a broader switch to 64-bit types for registers,
but it caused many problems. There are various places in code generation
where registers are not just treated as 32-bit numbers, but also treat
certain bit offsets as flags. So I limited the change as much as
possible to just the output of `getDwarfRegNum`. Keeping the types used
by `DwarfLLVMRegPair` as unsigned preserves the current behaviors. The
only way to give a 64-bit output from `getDwarfRegNum` that actually
needs more than 32-bits is to override `getDwarfRegNum` and provide an
implementation that sidesteps the use of the `DwarfLLVMRegPair` maps
defined in tablegen files.

First layer of stack supporting:
#109495

Author: willghatch

llvm/include/llvm/MC/MCRegisterInfo.h

@@ -418,15 +418,15 @@ class MCRegisterInfo {
   /// number.  Returns -1 if there is no equivalent value.  The second
   /// parameter allows targets to use different numberings for EH info and
   /// debugging info.
-  int getDwarfRegNum(MCRegister RegNum, bool isEH) const;
+  virtual int64_t getDwarfRegNum(MCRegister RegNum, bool isEH) const;
 
   /// Map a dwarf register back to a target register. Returns std::nullopt if
   /// there is no mapping.
-  std::optional<MCRegister> getLLVMRegNum(unsigned RegNum, bool isEH) const;
+  std::optional<MCRegister> getLLVMRegNum(uint64_t RegNum, bool isEH) const;
 
   /// Map a target EH register number to an equivalent DWARF register
   /// number.
-  int getDwarfRegNumFromDwarfEHRegNum(unsigned RegNum) const;
+  int64_t getDwarfRegNumFromDwarfEHRegNum(uint64_t RegNum) const;
 
   /// Map a target register to an equivalent SEH register
   /// number.  Returns LLVM register number if there is no equivalent value.

llvm/lib/CodeGen/AsmPrinter/DwarfDebug.cpp

@@ -570,15 +570,15 @@ void DwarfDebug::constructAbstractSubprogramScopeDIE(DwarfCompileUnit &SrcCU,
 /// debug expression to a register in the forwarded register worklist.
 struct FwdRegParamInfo {
   /// The described parameter register.
-  unsigned ParamReg;
+  uint64_t ParamReg;
 
   /// Debug expression that has been built up when walking through the
   /// instruction chain that produces the parameter's value.
   const DIExpression *Expr;
 };
 
 /// Register worklist for finding call site values.
-using FwdRegWorklist = MapVector<unsigned, SmallVector<FwdRegParamInfo, 2>>;
+using FwdRegWorklist = MapVector<uint64_t, SmallVector<FwdRegParamInfo, 2>>;
 /// Container for the set of registers known to be clobbered on the path to a
 /// call site.
 using ClobberedRegSet = SmallSet<Register, 16>;

llvm/lib/CodeGen/AsmPrinter/DwarfExpression.cpp

@@ -40,7 +40,7 @@ void DwarfExpression::emitConstu(uint64_t Value) {
   }
 }
 
-void DwarfExpression::addReg(int DwarfReg, const char *Comment) {
+void DwarfExpression::addReg(int64_t DwarfReg, const char *Comment) {
   assert(DwarfReg >= 0 && "invalid negative dwarf register number");
   assert((isUnknownLocation() || isRegisterLocation()) &&
          "location description already locked down");
@@ -53,7 +53,7 @@ void DwarfExpression::addReg(int DwarfReg, const char *Comment) {
   }
 }
 
-void DwarfExpression::addBReg(int DwarfReg, int Offset) {
+void DwarfExpression::addBReg(int64_t DwarfReg, int64_t Offset) {
   assert(DwarfReg >= 0 && "invalid negative dwarf register number");
   assert(!isRegisterLocation() && "location description already locked down");
   if (DwarfReg < 32) {
@@ -65,7 +65,7 @@ void DwarfExpression::addBReg(int DwarfReg, int Offset) {
   emitSigned(Offset);
 }
 
-void DwarfExpression::addFBReg(int Offset) {
+void DwarfExpression::addFBReg(int64_t Offset) {
   emitOp(dwarf::DW_OP_fbreg);
   emitSigned(Offset);
 }
@@ -108,7 +108,7 @@ bool DwarfExpression::addMachineReg(const TargetRegisterInfo &TRI,
     return false;
   }
 
-  int Reg = TRI.getDwarfRegNum(MachineReg, false);
+  int64_t Reg = TRI.getDwarfRegNum(MachineReg, false);
 
   // If this is a valid register number, emit it.
   if (Reg >= 0) {

llvm/lib/CodeGen/AsmPrinter/DwarfExpression.h

@@ -45,17 +45,17 @@ class DwarfExpression {
 protected:
   /// Holds information about all subregisters comprising a register location.
   struct Register {
-    int DwarfRegNo;
+    int64_t DwarfRegNo;
     unsigned SubRegSize;
     const char *Comment;
 
     /// Create a full register, no extra DW_OP_piece operators necessary.
-    static Register createRegister(int RegNo, const char *Comment) {
+    static Register createRegister(int64_t RegNo, const char *Comment) {
       return {RegNo, 0, Comment};
     }
 
     /// Create a subregister that needs a DW_OP_piece operator with SizeInBits.
-    static Register createSubRegister(int RegNo, unsigned SizeInBits,
+    static Register createSubRegister(int64_t RegNo, unsigned SizeInBits,
                                       const char *Comment) {
       return {RegNo, SizeInBits, Comment};
     }
@@ -161,13 +161,13 @@ class DwarfExpression {
 
   /// Emit a DW_OP_reg operation. Note that this is only legal inside a DWARF
   /// register location description.
-  void addReg(int DwarfReg, const char *Comment = nullptr);
+  void addReg(int64_t DwarfReg, const char *Comment = nullptr);
 
   /// Emit a DW_OP_breg operation.
-  void addBReg(int DwarfReg, int Offset);
+  void addBReg(int64_t DwarfReg, int64_t Offset);
 
   /// Emit DW_OP_fbreg <Offset>.
-  void addFBReg(int Offset);
+  void addFBReg(int64_t Offset);
 
   /// Emit a partial DWARF register operation.
   ///

llvm/lib/MC/MCRegisterInfo.cpp

@@ -141,7 +141,7 @@ unsigned MCRegisterInfo::getSubRegIndex(MCRegister Reg,
   return 0;
 }
 
-int MCRegisterInfo::getDwarfRegNum(MCRegister RegNum, bool isEH) const {
+int64_t MCRegisterInfo::getDwarfRegNum(MCRegister RegNum, bool isEH) const {
   const DwarfLLVMRegPair *M = isEH ? EHL2DwarfRegs : L2DwarfRegs;
   unsigned Size = isEH ? EHL2DwarfRegsSize : L2DwarfRegsSize;
 
@@ -151,24 +151,28 @@ int MCRegisterInfo::getDwarfRegNum(MCRegister RegNum, bool isEH) const {
   const DwarfLLVMRegPair *I = std::lower_bound(M, M+Size, Key);
   if (I == M+Size || I->FromReg != RegNum)
     return -1;
-  return I->ToReg;
+  // Consumers need to be able to detect -1 and -2, but at various points
+  // the numbers move between unsigned and signed representations, as well as
+  // between 32- and 64-bit representations. We need to convert first to int
+  // before int64_t for proper sign handling.
+  return int64_t(int(I->ToReg));
 }
 
-std::optional<MCRegister> MCRegisterInfo::getLLVMRegNum(unsigned RegNum,
+std::optional<MCRegister> MCRegisterInfo::getLLVMRegNum(uint64_t RegNum,
                                                         bool isEH) const {
   const DwarfLLVMRegPair *M = isEH ? EHDwarf2LRegs : Dwarf2LRegs;
   unsigned Size = isEH ? EHDwarf2LRegsSize : Dwarf2LRegsSize;
 
   if (!M)
     return std::nullopt;
-  DwarfLLVMRegPair Key = { RegNum, 0 };
+  DwarfLLVMRegPair Key = {unsigned(RegNum), 0};
   const DwarfLLVMRegPair *I = std::lower_bound(M, M+Size, Key);
   if (I != M + Size && I->FromReg == RegNum)
     return MCRegister::from(I->ToReg);
   return std::nullopt;
 }
 
-int MCRegisterInfo::getDwarfRegNumFromDwarfEHRegNum(unsigned RegNum) const {
+int64_t MCRegisterInfo::getDwarfRegNumFromDwarfEHRegNum(uint64_t RegNum) const {
   // On ELF platforms, DWARF EH register numbers are the same as DWARF
   // other register numbers.  On Darwin x86, they differ and so need to be
   // mapped.  The .cfi_* directives accept integer literals as well as

llvm/lib/Target/Lanai/LanaiRegisterInfo.h

@@ -43,8 +43,6 @@ struct LanaiRegisterInfo : public LanaiGenRegisterInfo {
   Register getFrameRegister(const MachineFunction &MF) const override;
   Register getBaseRegister() const;
   bool hasBasePointer(const MachineFunction &MF) const;
-
-  int getDwarfRegNum(unsigned RegNum, bool IsEH) const;
 };
 
 } // end namespace llvm