[dsymutil] Support and relocate base address selection entries for debug_loc

[JDevlieghere]

Summary

Since r374600 clang emits base address selection entries. Currently dsymutil does not support these entries and incorrectly interprets them as location list entries.

This patch adds support for base address selection entries in dsymutil and makes sure they are relocated correctly.

Thanks to Dave for coming up with the test case!

[dblaikie]

Looks right to me - but not 100% confident. Will leave it to Adrian/someone else more familiar with MachO/dsymutil/etc.

[aprantl]

llvm/tools/dsymutil/DwarfStreamer.cpp

402

BaseAddressMarker ?

llvm/test/tools/dsymutil/X86/debug-loc-base-addr.test

+RUN: dsymutil -oso-prepend-path %p/../Inputs %p/../Inputs/private/tmp/baseaddr/loc1.x86_64 -f -o - | llvm-dwarfdump -debug-loc - | FileCheck %s
+
+The test was compiled from a single source:
+$ cat loc1.cpp
+int f1(int i, int j) {
+  int x = 5;
+  int y = 3;
+  int r = i + j;
+  int undef;
+  x = undef;
+  y = 4;
+  return r;
+}
+__attribute__((nodebug)) void f2() {
+}
+int main() {
+  return 0;
+}
+
+CHECK: .debug_loc contents:
+CHECK: [0xffffffffffffffff,  0x0000000100000f90):
+CHECK: [0x0000000000000004,  0x0000000000000007): DW_OP_consts +3, DW_OP_stack_value
+CHECK: [0x0000000000000007,  0x0000000000000009): DW_OP_consts +4, DW_OP_stack_value
+
+CHECK: [0xffffffffffffffff,  0x0000000100000f90):
+CHECK: [0x0000000000000004,  0x0000000000000007): DW_OP_consts +5, DW_OP_stack_value
+
+CHECK: [0xffffffffffffffff,  0x0000000100000f90):
+CHECK: [0x0000000000000007,  0x0000000000000009): DW_OP_reg0 RAX

llvm/tools/dsymutil/DwarfStreamer.cpp

void DwarfStreamer::emitLocationsForUnit(
   const auto &Attributes = Unit.getLocationAttributes();
 
   if (Attributes.empty())
     return;
 
   MS->SwitchSection(MC->getObjectFileInfo()->getDwarfLocSection());
 
   unsigned AddressSize = Unit.getOrigUnit().getAddressByteSize();
+  uint64_t LargestRepresentable = (AddressSize == 8)
+                                      ? std::numeric_limits<uint64_t>::max()
+                                      : std::numeric_limits<uint32_t>::max();
   const DWARFSection &InputSec = Dwarf.getDWARFObj().getLocSection();
   DataExtractor Data(InputSec.Data, Dwarf.isLittleEndian(), AddressSize);
   DWARFUnit &OrigUnit = Unit.getOrigUnit();
   auto OrigUnitDie = OrigUnit.getUnitDIE(false);
   int64_t UnitPcOffset = 0;
   if (auto OrigLowPc = dwarf::toAddress(OrigUnitDie.find(dwarf::DW_AT_low_pc)))
     UnitPcOffset = int64_t(*OrigLowPc) - Unit.getLowPc();
 
   SmallVector<uint8_t, 32> Buffer;
   for (const auto &Attr : Attributes) {
     uint64_t Offset = Attr.first.get();
     Attr.first.set(LocSectionSize);
     // This is the quantity to add to the old location address to get
     // the correct address for the new one.
     int64_t LocPcOffset = Attr.second + UnitPcOffset;
     while (Data.isValidOffset(Offset)) {
       uint64_t Low = Data.getUnsigned(&Offset, AddressSize);
       uint64_t High = Data.getUnsigned(&Offset, AddressSize);
       LocSectionSize += 2 * AddressSize;
+      // End of list entry.
       if (Low == 0 && High == 0) {
         Asm->OutStreamer->EmitIntValue(0, AddressSize);
         Asm->OutStreamer->EmitIntValue(0, AddressSize);
         break;
       }
+      // Base address selection entry.
+      if (Low == LargestRepresentable) {
+        Asm->OutStreamer->EmitIntValue(LargestRepresentable, AddressSize);
+        Asm->OutStreamer->EmitIntValue(High + Attr.second, AddressSize);
+        LocPcOffset = 0;
+        continue;
+      }
+      // Location list entry.
       Asm->OutStreamer->EmitIntValue(Low + LocPcOffset, AddressSize);
       Asm->OutStreamer->EmitIntValue(High + LocPcOffset, AddressSize);
       uint64_t Length = Data.getU16(&Offset);
       Asm->OutStreamer->EmitIntValue(Length, 2);
       // Copy the bytes into to the buffer, process them, emit them.
       Buffer.reserve(Length);
       Buffer.resize(0);
       StringRef Input = InputSec.Data.substr(Offset, Length);