[llvm] Fix getting section info in large mach-o files. (PR #165940)

[Peter Rong via llvm-commits]

================
@@ -1978,20 +1978,34 @@ uint64_t MachOObjectFile::getSectionSize(DataRefImpl Sec) const {
   return SectSize;
 }
 
-ArrayRef<uint8_t> MachOObjectFile::getSectionContents(uint32_t Offset,
+ArrayRef<uint8_t> MachOObjectFile::getSectionContents(uint64_t Offset,
                                                       uint64_t Size) const {
   return arrayRefFromStringRef(getData().substr(Offset, Size));
 }
 
 Expected<ArrayRef<uint8_t>>
 MachOObjectFile::getSectionContents(DataRefImpl Sec) const {
-  uint32_t Offset;
+  uint64_t Offset;
   uint64_t Size;
 
   if (is64Bit()) {
     MachO::section_64 Sect = getSection64(Sec);
     Offset = Sect.offset;
     Size = Sect.size;
+    // Check for large mach-o files where the section contents might exceed
+    // 4GB. MachO::section_64 objects only have 32 bit file offsets to the
+    // section contents and can overflow in dSYM files. We can track this and
+    // adjust the section offset to be 64 bit safe.
+    uint64_t SectOffsetAdjust = 0;
+    for (uint32_t SectIdx=0; SectIdx<Sec.d.a; ++SectIdx) {
+      MachO::section_64 CurrSect =
+          getStruct<MachO::section_64>(*this, Sections[SectIdx]);
+      const uint64_t EndSectFileOffset =
+          (uint64_t)CurrSect.offset + CurrSect.size;
+      if (EndSectFileOffset >= UINT32_MAX)
+        SectOffsetAdjust += EndSectFileOffset & 0xFFFFFFFF00000000ull;
+    }
----------------
DataCorrupted wrote:

Another approach I might suggest is guard this extension behind some flags

cc @drodriguez 

https://github.com/llvm/llvm-project/pull/165940