[lld][llvm/mc] Add support for sdata8 for FDE CIE

lld/test/ELF/eh-frame-large-fde-encoding.s

@@ -0,0 +1,45 @@
+# REQUIRES: x86
+
+## Test that demonstrates FDE encoding overflow when .eh_frame is placed
+## far from .text, and the fix using 8-byte (sdata8) FDE encoding.
+##
+## With the default 4-byte FDE encoding (sdata4), a PC-relative offset
+## to .text can overflow if .eh_frame is placed more than 2GB away.
+## Using -large-fde-encoding (or mcmodel=large) switches to 8-byte
+## FDE encoding which can address the full 64-bit address space.
+
+# RUN: rm -rf %t && split-file %s %t
+
+## Test 1: With default sdata4 encoding, placing .eh_frame far from .text
+## causes an overflow error.
+# RUN: llvm-mc -filetype=obj -triple=x86_64-linux-gnu --large-fde-encoding=false \
+# RUN:   %t/test.s -o %t/test-small.o
+# RUN: not ld.lld %t/test-small.o -T %t/far.lds -o /dev/null 2>&1 | \
+# RUN:   FileCheck %s --check-prefix=OVERFLOW
+
+## Test 2: With sdata8 encoding via -large-fde-encoding, no overflow.
+# RUN: llvm-mc -filetype=obj -triple=x86_64-linux-gnu -large-fde-encoding \
+# RUN:   %t/test.s -o %t/test-large.o
+# RUN: ld.lld %t/test-large.o -T %t/far.lds -o %t/out
+
+# OVERFLOW: ld.lld: error: <internal>:(.eh_frame+0x{{[0-9a-fA-F]+}}): relocation R_X86_64_PC32 out of range
+
+#--- test.s
+.text
+.globl _start
+.type _start, @function
+_start:
+  .cfi_startproc
+  ret
+  .cfi_endproc
+
+#--- far.lds
+SECTIONS {
+  ## Place .text at a low address
+  . = 0x1000;
+  .text : { *(.text) }
+
+  ## Place .eh_frame more than 2GB away to trigger overflow with sdata4
+  . = 0x100001000;
+  .eh_frame : { *(.eh_frame) }
+}

llvm/include/llvm/MC/MCTargetOptions.h

@@ -108,6 +108,10 @@ class MCTargetOptions {
   // Whether or not to use full register names on PowerPC.
   bool PPCUseFullRegisterNames : 1;
 
+  // Use 8-byte pointer size for ELF FDE CFI encoding, regardless of code model.
+  // Useful when text sections may exceed 2GB even with medium code model
+  bool LargeFDEEncoding : 1;
+
   LLVM_ABI MCTargetOptions();
 
   /// getABIName - If this returns a non-empty string this represents the

llvm/include/llvm/MC/MCTargetOptionsCommandFlags.h

@@ -63,6 +63,8 @@ LLVM_ABI bool getX86RelaxRelocations();
 
 LLVM_ABI bool getX86Sse2Avx();
 
+LLVM_ABI bool getLargeFDEEncoding();
+
 LLVM_ABI StringRef getABIName();
 
 LLVM_ABI StringRef getAsSecureLogFile();

llvm/lib/MC/MCObjectFileInfo.cpp

@@ -24,6 +24,7 @@
 #include "llvm/MC/MCSectionSPIRV.h"
 #include "llvm/MC/MCSectionWasm.h"
 #include "llvm/MC/MCSectionXCOFF.h"
+#include "llvm/MC/MCTargetOptions.h"
 #include "llvm/TargetParser/Triple.h"
 
 using namespace llvm;
@@ -332,7 +333,6 @@ void MCObjectFileInfo::initMachOMCObjectFileInfo(const Triple &T) {
 
   TLSExtraDataSection = TLSTLVSection;
 }
-
 void MCObjectFileInfo::initELFMCObjectFileInfo(const Triple &T, bool Large) {
   switch (T.getArch()) {
   case Triple::mips:
@@ -354,10 +354,15 @@ void MCObjectFileInfo::initELFMCObjectFileInfo(const Triple &T, bool Large) {
   case Triple::ppc64le:
   case Triple::aarch64:
   case Triple::aarch64_be:
-  case Triple::x86_64:
-    FDECFIEncoding = dwarf::DW_EH_PE_pcrel |
-                     (Large ? dwarf::DW_EH_PE_sdata8 : dwarf::DW_EH_PE_sdata4);
+  case Triple::x86_64: {
+    // Check if the user requested large FDE encoding via MCTargetOptions
+    const MCTargetOptions *TO = Ctx->getTargetOptions();
+    bool Use8ByteFDE = Large || (TO && TO->LargeFDEEncoding);
+    FDECFIEncoding =
+        dwarf::DW_EH_PE_pcrel |
+        (Use8ByteFDE ? dwarf::DW_EH_PE_sdata8 : dwarf::DW_EH_PE_sdata4);
     break;
+  }
   case Triple::bpfel:
   case Triple::bpfeb:
     FDECFIEncoding = dwarf::DW_EH_PE_sdata8;

llvm/lib/MC/MCTargetOptions.cpp

@@ -20,11 +20,9 @@ MCTargetOptions::MCTargetOptions()
       EmitDwarfUnwind(EmitDwarfUnwindType::Default),
       MCUseDwarfDirectory(DefaultDwarfDirectory),
       EmitCompactUnwindNonCanonical(false), EmitSFrameUnwind(false),
-      PPCUseFullRegisterNames(false) {}
+      PPCUseFullRegisterNames(false), LargeFDEEncoding(false) {}
 
-StringRef MCTargetOptions::getABIName() const {
-  return ABIName;
-}
+StringRef MCTargetOptions::getABIName() const { return ABIName; }
 
 StringRef MCTargetOptions::getAssemblyLanguage() const {
   return AssemblyLanguage;

llvm/lib/MC/MCTargetOptionsCommandFlags.cpp

@@ -59,6 +59,7 @@ MCOPT(bool, Crel)
 MCOPT(bool, ImplicitMapSyms)
 MCOPT(bool, X86RelaxRelocations)
 MCOPT(bool, X86Sse2Avx)
+MCOPT(bool, LargeFDEEncoding)
 MCSTROPT(ABIName)
 MCSTROPT(AsSecureLogFile)
 
@@ -168,6 +169,13 @@ llvm::mc::RegisterMCTargetOptionsFlags::RegisterMCTargetOptionsFlags() {
                               "instructions with VEX prefix"));
   MCBINDOPT(X86Sse2Avx);
 
+  static cl::opt<bool> LargeFDEEncoding(
+      "large-fde-encoding",
+      cl::desc("Use 8-byte pointer size for ELF FDE CFI encoding, useful "
+               "when text sections may exceed 2GB even with medium code"),
+      cl::init(false));
+  MCBINDOPT(LargeFDEEncoding);
+
   static cl::opt<std::string> ABIName(
       "target-abi",
       cl::desc("The name of the ABI to be targeted from the backend."),
@@ -199,6 +207,7 @@ MCTargetOptions llvm::mc::InitMCTargetOptionsFromFlags() {
   Options.ImplicitMapSyms = getImplicitMapSyms();
   Options.X86RelaxRelocations = getX86RelaxRelocations();
   Options.X86Sse2Avx = getX86Sse2Avx();
+  Options.LargeFDEEncoding = getLargeFDEEncoding();
   Options.EmitDwarfUnwind = getEmitDwarfUnwind();
   Options.EmitCompactUnwindNonCanonical = getEmitCompactUnwindNonCanonical();
   Options.EmitSFrameUnwind = getEmitSFrameUnwind();