Update frame layout & CFI generation to handle frames larger than 2gb

For very large stack frames, the offset from the stack pointer to a
local can be more than 2^31 which overflows various `int` offsets
in the frame lowering code.

This patch updates the frame lowering code to calculate the offsets as
64-bit values and fixes CFI to use the corrected sizes.

After this patch, additional work is needed to fix offset truncations in
each target's codegen.

Author: wesleywiser

llvm/include/llvm/CodeGen/MachineFrameInfo.h

@@ -251,7 +251,7 @@ class MachineFrameInfo {
   /// targets, this value is only used when generating debug info (via
   /// TargetRegisterInfo::getFrameIndexReference); when generating code, the
   /// corresponding adjustments are performed directly.
-  int OffsetAdjustment = 0;
+  int64_t OffsetAdjustment = 0;
 
   /// The prolog/epilog code inserter may process objects that require greater
   /// alignment than the default alignment the target provides.
@@ -280,7 +280,7 @@ class MachineFrameInfo {
   /// setup/destroy pseudo instructions (as defined in the TargetFrameInfo
   /// class).  This information is important for frame pointer elimination.
   /// It is only valid during and after prolog/epilog code insertion.
-  unsigned MaxCallFrameSize = ~0u;
+  uint64_t MaxCallFrameSize = ~UINT64_C(0);
 
   /// The number of bytes of callee saved registers that the target wants to
   /// report for the current function in the CodeView S_FRAMEPROC record.
@@ -593,10 +593,10 @@ class MachineFrameInfo {
   uint64_t estimateStackSize(const MachineFunction &MF) const;
 
   /// Return the correction for frame offsets.
-  int getOffsetAdjustment() const { return OffsetAdjustment; }
+  int64_t getOffsetAdjustment() const { return OffsetAdjustment; }
 
   /// Set the correction for frame offsets.
-  void setOffsetAdjustment(int Adj) { OffsetAdjustment = Adj; }
+  void setOffsetAdjustment(int64_t Adj) { OffsetAdjustment = Adj; }
 
   /// Return the alignment in bytes that this function must be aligned to,
   /// which is greater than the default stack alignment provided by the target.
@@ -663,17 +663,17 @@ class MachineFrameInfo {
   /// CallFrameSetup/Destroy pseudo instructions are used by the target, and
   /// then only during or after prolog/epilog code insertion.
   ///
-  unsigned getMaxCallFrameSize() const {
+  uint64_t getMaxCallFrameSize() const {
     // TODO: Enable this assert when targets are fixed.
     //assert(isMaxCallFrameSizeComputed() && "MaxCallFrameSize not computed yet");
     if (!isMaxCallFrameSizeComputed())
       return 0;
     return MaxCallFrameSize;
   }
   bool isMaxCallFrameSizeComputed() const {
-    return MaxCallFrameSize != ~0u;
+    return MaxCallFrameSize != ~UINT64_C(0);
   }
-  void setMaxCallFrameSize(unsigned S) { MaxCallFrameSize = S; }
+  void setMaxCallFrameSize(uint64_t S) { MaxCallFrameSize = S; }
 
   /// Returns how many bytes of callee-saved registers the target pushed in the
   /// prologue. Only used for debug info.

llvm/include/llvm/CodeGen/TargetFrameLowering.h

@@ -51,7 +51,7 @@ class TargetFrameLowering {
   // Maps a callee saved register to a stack slot with a fixed offset.
   struct SpillSlot {
     unsigned Reg;
-    int Offset; // Offset relative to stack pointer on function entry.
+    int64_t Offset; // Offset relative to stack pointer on function entry.
   };
 
   struct DwarfFrameBase {
@@ -66,7 +66,7 @@ class TargetFrameLowering {
       // Used with FrameBaseKind::Register.
       unsigned Reg;
       // Used with FrameBaseKind::CFA.
-      int Offset;
+      int64_t Offset;
       struct WasmFrameBase WasmLoc;
     } Location;
   };

llvm/include/llvm/MC/MCAsmBackend.h

@@ -224,7 +224,7 @@ class MCAsmBackend {
   virtual void handleAssemblerFlag(MCAssemblerFlag Flag) {}
 
   /// Generate the compact unwind encoding for the CFI instructions.
-  virtual uint32_t generateCompactUnwindEncoding(const MCDwarfFrameInfo *FI,
+  virtual uint64_t generateCompactUnwindEncoding(const MCDwarfFrameInfo *FI,
                                                  const MCContext *Ctxt) const {
     return 0;
   }

llvm/include/llvm/MC/MCDwarf.h

@@ -509,11 +509,11 @@ class MCCFIInstruction {
   union {
     struct {
       unsigned Register;
-      int Offset;
+      int64_t Offset;
     } RI;
     struct {
       unsigned Register;
-      int Offset;
+      int64_t Offset;
       unsigned AddressSpace;
     } RIA;
     struct {
@@ -527,7 +527,7 @@ class MCCFIInstruction {
   std::vector<char> Values;
   std::string Comment;
 
-  MCCFIInstruction(OpType Op, MCSymbol *L, unsigned R, int O, SMLoc Loc,
+  MCCFIInstruction(OpType Op, MCSymbol *L, unsigned R, int64_t O, SMLoc Loc,
                    StringRef V = "", StringRef Comment = "")
       : Label(L), Operation(Op), Loc(Loc), Values(V.begin(), V.end()),
         Comment(Comment) {
@@ -539,7 +539,7 @@ class MCCFIInstruction {
     assert(Op == OpRegister);
     U.RR = {R1, R2};
   }
-  MCCFIInstruction(OpType Op, MCSymbol *L, unsigned R, int O, unsigned AS,
+  MCCFIInstruction(OpType Op, MCSymbol *L, unsigned R, int64_t O, unsigned AS,
                    SMLoc Loc)
       : Label(L), Operation(Op), Loc(Loc) {
     assert(Op == OpLLVMDefAspaceCfa);
@@ -555,30 +555,30 @@ class MCCFIInstruction {
 public:
   /// .cfi_def_cfa defines a rule for computing CFA as: take address from
   /// Register and add Offset to it.
-  static MCCFIInstruction cfiDefCfa(MCSymbol *L, unsigned Register, int Offset,
-                                    SMLoc Loc = {}) {
+  static MCCFIInstruction cfiDefCfa(MCSymbol *L, unsigned Register,
+                                    int64_t Offset, SMLoc Loc = {}) {
     return MCCFIInstruction(OpDefCfa, L, Register, Offset, Loc);
   }
 
   /// .cfi_def_cfa_register modifies a rule for computing CFA. From now
   /// on Register will be used instead of the old one. Offset remains the same.
   static MCCFIInstruction createDefCfaRegister(MCSymbol *L, unsigned Register,
                                                SMLoc Loc = {}) {
-    return MCCFIInstruction(OpDefCfaRegister, L, Register, 0, Loc);
+    return MCCFIInstruction(OpDefCfaRegister, L, Register, INT64_C(0), Loc);
   }
 
   /// .cfi_def_cfa_offset modifies a rule for computing CFA. Register
   /// remains the same, but offset is new. Note that it is the absolute offset
   /// that will be added to a defined register to the compute CFA address.
-  static MCCFIInstruction cfiDefCfaOffset(MCSymbol *L, int Offset,
+  static MCCFIInstruction cfiDefCfaOffset(MCSymbol *L, int64_t Offset,
                                           SMLoc Loc = {}) {
     return MCCFIInstruction(OpDefCfaOffset, L, 0, Offset, Loc);
   }
 
   /// .cfi_adjust_cfa_offset Same as .cfi_def_cfa_offset, but
   /// Offset is a relative value that is added/subtracted from the previous
   /// offset.
-  static MCCFIInstruction createAdjustCfaOffset(MCSymbol *L, int Adjustment,
+  static MCCFIInstruction createAdjustCfaOffset(MCSymbol *L, int64_t Adjustment,
                                                 SMLoc Loc = {}) {
     return MCCFIInstruction(OpAdjustCfaOffset, L, 0, Adjustment, Loc);
   }
@@ -588,7 +588,7 @@ class MCCFIInstruction {
   /// be the result of evaluating the DWARF operation expression
   /// `DW_OP_constu AS; DW_OP_aspace_bregx R, B` as a location description.
   static MCCFIInstruction createLLVMDefAspaceCfa(MCSymbol *L, unsigned Register,
-                                                 int Offset,
+                                                 int64_t Offset,
                                                  unsigned AddressSpace,
                                                  SMLoc Loc) {
     return MCCFIInstruction(OpLLVMDefAspaceCfa, L, Register, Offset,
@@ -598,15 +598,15 @@ class MCCFIInstruction {
   /// .cfi_offset Previous value of Register is saved at offset Offset
   /// from CFA.
   static MCCFIInstruction createOffset(MCSymbol *L, unsigned Register,
-                                       int Offset, SMLoc Loc = {}) {
+                                       int64_t Offset, SMLoc Loc = {}) {
     return MCCFIInstruction(OpOffset, L, Register, Offset, Loc);
   }
 
   /// .cfi_rel_offset Previous value of Register is saved at offset
   /// Offset from the current CFA register. This is transformed to .cfi_offset
   /// using the known displacement of the CFA register from the CFA.
   static MCCFIInstruction createRelOffset(MCSymbol *L, unsigned Register,
-                                          int Offset, SMLoc Loc = {}) {
+                                          int64_t Offset, SMLoc Loc = {}) {
     return MCCFIInstruction(OpRelOffset, L, Register, Offset, Loc);
   }
 
@@ -619,44 +619,44 @@ class MCCFIInstruction {
 
   /// .cfi_window_save SPARC register window is saved.
   static MCCFIInstruction createWindowSave(MCSymbol *L, SMLoc Loc = {}) {
-    return MCCFIInstruction(OpWindowSave, L, 0, 0, Loc);
+    return MCCFIInstruction(OpWindowSave, L, 0, INT64_C(0), Loc);
   }
 
   /// .cfi_negate_ra_state AArch64 negate RA state.
   static MCCFIInstruction createNegateRAState(MCSymbol *L, SMLoc Loc = {}) {
-    return MCCFIInstruction(OpNegateRAState, L, 0, 0, Loc);
+    return MCCFIInstruction(OpNegateRAState, L, 0, INT64_C(0), Loc);
   }
 
   /// .cfi_restore says that the rule for Register is now the same as it
   /// was at the beginning of the function, after all initial instructions added
   /// by .cfi_startproc were executed.
   static MCCFIInstruction createRestore(MCSymbol *L, unsigned Register,
                                         SMLoc Loc = {}) {
-    return MCCFIInstruction(OpRestore, L, Register, 0, Loc);
+    return MCCFIInstruction(OpRestore, L, Register, INT64_C(0), Loc);
   }
 
   /// .cfi_undefined From now on the previous value of Register can't be
   /// restored anymore.
   static MCCFIInstruction createUndefined(MCSymbol *L, unsigned Register,
                                           SMLoc Loc = {}) {
-    return MCCFIInstruction(OpUndefined, L, Register, 0, Loc);
+    return MCCFIInstruction(OpUndefined, L, Register, INT64_C(0), Loc);
   }
 
   /// .cfi_same_value Current value of Register is the same as in the
   /// previous frame. I.e., no restoration is needed.
   static MCCFIInstruction createSameValue(MCSymbol *L, unsigned Register,
                                           SMLoc Loc = {}) {
-    return MCCFIInstruction(OpSameValue, L, Register, 0, Loc);
+    return MCCFIInstruction(OpSameValue, L, Register, INT64_C(0), Loc);
   }
 
   /// .cfi_remember_state Save all current rules for all registers.
   static MCCFIInstruction createRememberState(MCSymbol *L, SMLoc Loc = {}) {
-    return MCCFIInstruction(OpRememberState, L, 0, 0, Loc);
+    return MCCFIInstruction(OpRememberState, L, 0, INT64_C(0), Loc);
   }
 
   /// .cfi_restore_state Restore the previously saved state.
   static MCCFIInstruction createRestoreState(MCSymbol *L, SMLoc Loc = {}) {
-    return MCCFIInstruction(OpRestoreState, L, 0, 0, Loc);
+    return MCCFIInstruction(OpRestoreState, L, 0, INT64_C(0), Loc);
   }
 
   /// .cfi_escape Allows the user to add arbitrary bytes to the unwind
@@ -667,7 +667,7 @@ class MCCFIInstruction {
   }
 
   /// A special wrapper for .cfi_escape that indicates GNU_ARGS_SIZE
-  static MCCFIInstruction createGnuArgsSize(MCSymbol *L, int Size,
+  static MCCFIInstruction createGnuArgsSize(MCSymbol *L, int64_t Size,
                                             SMLoc Loc = {}) {
     return MCCFIInstruction(OpGnuArgsSize, L, 0, Size, Loc);
   }
@@ -702,7 +702,7 @@ class MCCFIInstruction {
     return U.RIA.AddressSpace;
   }
 
-  int getOffset() const {
+  int64_t getOffset() const {
     if (Operation == OpLLVMDefAspaceCfa)
       return U.RIA.Offset;
     assert(Operation == OpDefCfa || Operation == OpOffset ||
@@ -736,7 +736,7 @@ struct MCDwarfFrameInfo {
   unsigned CurrentCfaRegister = 0;
   unsigned PersonalityEncoding = 0;
   unsigned LsdaEncoding = 0;
-  uint32_t CompactUnwindEncoding = 0;
+  uint64_t CompactUnwindEncoding = 0;
   bool IsSignalFrame = false;
   bool IsSimple = false;
   unsigned RAReg = static_cast<unsigned>(INT_MAX);

llvm/lib/CodeGen/CFIInstrInserter.cpp

@@ -68,9 +68,9 @@ class CFIInstrInserter : public MachineFunctionPass {
   struct MBBCFAInfo {
     MachineBasicBlock *MBB;
     /// Value of cfa offset valid at basic block entry.
-    int IncomingCFAOffset = -1;
+    int64_t IncomingCFAOffset = -1;
     /// Value of cfa offset valid at basic block exit.
-    int OutgoingCFAOffset = -1;
+    int64_t OutgoingCFAOffset = -1;
     /// Value of cfa register valid at basic block entry.
     unsigned IncomingCFARegister = 0;
     /// Value of cfa register valid at basic block exit.
@@ -120,7 +120,7 @@ class CFIInstrInserter : public MachineFunctionPass {
   /// Return the cfa offset value that should be set at the beginning of a MBB
   /// if needed. The negated value is needed when creating CFI instructions that
   /// set absolute offset.
-  int getCorrectCFAOffset(MachineBasicBlock *MBB) {
+  int64_t getCorrectCFAOffset(MachineBasicBlock *MBB) {
     return MBBVector[MBB->getNumber()].IncomingCFAOffset;
   }
 
@@ -175,7 +175,7 @@ void CFIInstrInserter::calculateCFAInfo(MachineFunction &MF) {
 
 void CFIInstrInserter::calculateOutgoingCFAInfo(MBBCFAInfo &MBBInfo) {
   // Outgoing cfa offset set by the block.
-  int SetOffset = MBBInfo.IncomingCFAOffset;
+  int64_t SetOffset = MBBInfo.IncomingCFAOffset;
   // Outgoing cfa register set by the block.
   unsigned SetRegister = MBBInfo.IncomingCFARegister;
   MachineFunction *MF = MBBInfo.MBB->getParent();
@@ -188,7 +188,7 @@ void CFIInstrInserter::calculateOutgoingCFAInfo(MBBCFAInfo &MBBInfo) {
   for (MachineInstr &MI : *MBBInfo.MBB) {
     if (MI.isCFIInstruction()) {
       std::optional<unsigned> CSRReg;
-      std::optional<int> CSROffset;
+      std::optional<int64_t> CSROffset;
       unsigned CFIIndex = MI.getOperand(0).getCFIIndex();
       const MCCFIInstruction &CFI = Instrs[CFIIndex];
       switch (CFI.getOperation()) {

llvm/lib/CodeGen/MachineFrameInfo.cpp

@@ -197,7 +197,7 @@ void MachineFrameInfo::computeMaxCallFrameSize(
     for (MachineInstr &MI : MBB) {
       unsigned Opcode = MI.getOpcode();
       if (Opcode == FrameSetupOpcode || Opcode == FrameDestroyOpcode) {
-        unsigned Size = TII.getFrameSize(MI);
+        uint64_t Size = TII.getFrameSize(MI);
         MaxCallFrameSize = std::max(MaxCallFrameSize, Size);
         if (FrameSDOps != nullptr)
           FrameSDOps->push_back(&MI);

llvm/lib/CodeGen/PrologEpilogInserter.cpp

@@ -366,8 +366,8 @@ void PEI::calculateCallFrameInfo(MachineFunction &MF) {
     return;
 
   // (Re-)Compute the MaxCallFrameSize.
-  [[maybe_unused]] uint32_t MaxCFSIn =
-      MFI.isMaxCallFrameSizeComputed() ? MFI.getMaxCallFrameSize() : UINT32_MAX;
+  [[maybe_unused]] uint64_t MaxCFSIn =
+      MFI.isMaxCallFrameSizeComputed() ? MFI.getMaxCallFrameSize() : UINT64_MAX;
   std::vector<MachineBasicBlock::iterator> FrameSDOps;
   MFI.computeMaxCallFrameSize(MF, &FrameSDOps);
   assert(MFI.getMaxCallFrameSize() <= MaxCFSIn &&

llvm/lib/MC/MCDwarf.cpp

@@ -1299,8 +1299,8 @@ static void EmitPersonality(MCStreamer &streamer, const MCSymbol &symbol,
 namespace {
 
 class FrameEmitterImpl {
-  int CFAOffset = 0;
-  int InitialCFAOffset = 0;
+  int64_t CFAOffset = 0;
+  int64_t InitialCFAOffset = 0;
   bool IsEH;
   MCObjectStreamer &Streamer;
 
@@ -1414,7 +1414,7 @@ void FrameEmitterImpl::emitCFIInstruction(const MCCFIInstruction &Instr) {
     if (!IsEH)
       Reg = MRI->getDwarfRegNumFromDwarfEHRegNum(Reg);
 
-    int Offset = Instr.getOffset();
+    int64_t Offset = Instr.getOffset();
     if (IsRelative)
       Offset -= CFAOffset;
     Offset = Offset / dataAlignmentFactor;

llvm/lib/Target/AArch64/MCTargetDesc/AArch64AsmBackend.cpp

@@ -599,7 +599,7 @@ class DarwinAArch64AsmBackend : public AArch64AsmBackend {
   }
 
   /// Generate the compact unwind encoding from the CFI directives.
-  uint32_t generateCompactUnwindEncoding(const MCDwarfFrameInfo *FI,
+  uint64_t generateCompactUnwindEncoding(const MCDwarfFrameInfo *FI,
                                          const MCContext *Ctxt) const override {
     ArrayRef<MCCFIInstruction> Instrs = FI->Instructions;
     if (Instrs.empty())
@@ -609,10 +609,10 @@ class DarwinAArch64AsmBackend : public AArch64AsmBackend {
       return CU::UNWIND_ARM64_MODE_DWARF;
 
     bool HasFP = false;
-    unsigned StackSize = 0;
+    uint64_t StackSize = 0;
 
-    uint32_t CompactUnwindEncoding = 0;
-    int CurOffset = 0;
+    uint64_t CompactUnwindEncoding = 0;
+    int64_t CurOffset = 0;
     for (size_t i = 0, e = Instrs.size(); i != e; ++i) {
       const MCCFIInstruction &Inst = Instrs[i];
 

llvm/lib/Target/ARM/ARMFrameLowering.cpp

@@ -1167,7 +1167,7 @@ void ARMFrameLowering::emitPrologue(MachineFunction &MF,
         if (STI.splitFramePushPop(MF)) {
           unsigned DwarfReg = MRI->getDwarfRegNum(
               Reg == ARM::R12 ? ARM::RA_AUTH_CODE : Reg, true);
-          unsigned Offset = MFI.getObjectOffset(FI);
+          int64_t Offset = MFI.getObjectOffset(FI);
           unsigned CFIIndex = MF.addFrameInst(
               MCCFIInstruction::createOffset(nullptr, DwarfReg, Offset));
           BuildMI(MBB, Pos, dl, TII.get(TargetOpcode::CFI_INSTRUCTION))
@@ -1189,7 +1189,7 @@ void ARMFrameLowering::emitPrologue(MachineFunction &MF,
       if ((Reg >= ARM::D0 && Reg <= ARM::D31) &&
           (Reg < ARM::D8 || Reg >= ARM::D8 + AFI->getNumAlignedDPRCS2Regs())) {
         unsigned DwarfReg = MRI->getDwarfRegNum(Reg, true);
-        unsigned Offset = MFI.getObjectOffset(FI);
+        int64_t Offset = MFI.getObjectOffset(FI);
         unsigned CFIIndex = MF.addFrameInst(
             MCCFIInstruction::createOffset(nullptr, DwarfReg, Offset));
         BuildMI(MBB, Pos, dl, TII.get(TargetOpcode::CFI_INSTRUCTION))