[BOLT][DWARF] Fix handling of invalid DIE references

Compiler can generate DIE References that are invalid. Previously BOLT could
assert when writing out IR to .debug_info. Changed where DIE offsets are changed
so that it's always done. Thus making sure that assert is not triggered.

Added more specific warnings, and ability to print out invalid referenced DIE
offset when verbosity >=1.

Reviewed By: Amir

Differential Revision: https://reviews.llvm.org/D157746

Author: ayermolo

bolt/include/bolt/Core/DIEBuilder.h

@@ -21,12 +21,12 @@
 #include "llvm/DebugInfo/DWARF/DWARFExpression.h"
 #include "llvm/DebugInfo/DWARF/DWARFUnit.h"
 #include "llvm/Support/Allocator.h"
-#include "llvm/Support/ErrorHandling.h"
 
 #include <list>
 #include <memory>
 #include <optional>
 #include <unordered_map>
+#include <unordered_set>
 #include <vector>
 
 namespace llvm {
@@ -113,6 +113,7 @@ class DIEBuilder {
     std::vector<LocWithReference> LocWithReferencesToProcess;
     BumpPtrAllocator DIEAlloc;
     ProcessingType Type;
+    std::unordered_set<uint64_t> DWARFDieAddressesParsed;
   };
 
   std::unique_ptr<State> BuilderState;

bolt/lib/Core/DIEBuilder.cpp

@@ -39,6 +39,9 @@
 
 #undef DEBUG_TYPE
 #define DEBUG_TYPE "bolt"
+namespace opts {
+extern cl::opt<unsigned> Verbosity;
+}
 namespace llvm {
 namespace bolt {
 
@@ -105,6 +108,14 @@ uint32_t DIEBuilder::allocDIE(const DWARFUnit &DU, const DWARFDie &DDie,
     return DWARFUnitInfo.DIEIDMap[DDieOffset];
 
   DIE *Die = DIE::get(Alloc, dwarf::Tag(DDie.getTag()));
+  // This handles the case where there is a DIE ref which points to
+  // invalid DIE. This prevents assert when IR is written out.
+  // Also it makes debugging easier.
+  // DIE dump is not very useful.
+  // It's nice to know original offset from which this DIE was constructed.
+  Die->setOffset(DDie.getOffset());
+  if (opts::Verbosity >= 1)
+    getState().DWARFDieAddressesParsed.insert(DDie.getOffset());
   const uint32_t DId = DWARFUnitInfo.DieInfoVector.size();
   DWARFUnitInfo.DIEIDMap[DDieOffset] = DId;
   DWARFUnitInfo.DieInfoVector.emplace_back(
@@ -290,10 +301,6 @@ DIE *DIEBuilder::constructDIEFast(DWARFDie &DDie, DWARFUnit &U,
   DIEInfo &DieInfo = getDIEInfo(UnitId, *Idx);
 
   uint64_t Offset = DDie.getOffset();
-  // Just for making debugging easier.
-  // DIE dump is not very useful.
-  // It's nice to know original offset from which this DIE was constructed.
-  DieInfo.Die->setOffset(Offset);
   uint64_t NextOffset = Offset;
   DWARFDataExtractor Data = U.getDebugInfoExtractor();
   DWARFDebugInfoEntry DDIEntry;
@@ -369,6 +376,7 @@ getUnitForOffset(DIEBuilder &Builder, DWARFContext &DWCtx,
 
 uint32_t DIEBuilder::computeDIEOffset(const DWARFUnit &CU, DIE &Die,
                                       uint32_t &CurOffset) {
+  getState().DWARFDieAddressesParsed.erase(Die.getOffset());
   uint32_t CurSize = 0;
   Die.setOffset(CurOffset);
   for (DIEValue &Val : Die.values())
@@ -421,6 +429,13 @@ void DIEBuilder::finish() {
       continue;
     computeOffset(*CU, UnitSize);
   }
+  if (opts::Verbosity >= 1) {
+    if (!getState().DWARFDieAddressesParsed.empty())
+      dbgs() << "Referenced DIE offsets not in .debug_info\n";
+    for (const uint64_t Address : getState().DWARFDieAddressesParsed) {
+      dbgs() << Twine::utohexstr(Address) << "\n";
+    }
+  }
   updateReferences();
 }
 
@@ -457,11 +472,20 @@ DWARFDie DIEBuilder::resolveDIEReference(
           allocDIE(*RefCU, RefDie, getState().DIEAlloc, *UnitId);
         return RefDie;
       }
+      errs() << "BOLT-WARNING: [internal-dwarf-error]: invalid referenced DIE "
+                "at offset: "
+             << Twine::utohexstr(RefOffset) << ".\n";
+
+    } else {
+      errs() << "BOLT-WARNING: [internal-dwarf-error]: could not parse "
+                "referenced DIE at offset: "
+             << Twine::utohexstr(RefOffset) << ".\n";
     }
+  } else {
+    errs() << "BOLT-WARNING: [internal-dwarf-error]: could not find referenced "
+              "CU. Referenced DIE offset: "
+           << Twine::utohexstr(RefOffset) << ".\n";
   }
-
-  errs() << "BOLT-WARNING: [internal-dwarf-error]: could not find referenced "
-            "CU.\n";
   return DWARFDie();
 }