[CodeView] Align type records on 4-bytes when emitting PDBs

When emitting PDBs, the TypeStreamMerger class is used to merge .debug$T records from the input .OBJ files into the output .PDB stream.
Records in .OBJs are not required to be aligned on 4-bytes, and "The Netwide Assembler 2.14" generates non-aligned records.

When compiling with -DLLVM_ENABLE_ASSERTIONS=ON, an assert was triggered in MergingTypeTableBuilder when non-ghash merging was used.
With ghash merging there was no assert.
As a result, LLD could potentially generate a non-aligned TPI stream.

We now align records on 4-bytes when record indices are remapped, in TypeStreamMerger::remapIndices().

Differential Revision: https://reviews.llvm.org/D75081

(cherry picked from commit a7325298e1f311b383b8ce5ba8e2d3698fef472a)

3 files changed, 32 insertions, 6 deletions

diff --git a/llvm/lib/DebugInfo/CodeView/MergingTypeTableBuilder.cpp b/llvm/lib/DebugInfo/CodeView/MergingTypeTableBuilder.cpp
index 4d7cd468f3e..6924b0e0ca0 100644
--- a/llvm/lib/DebugInfo/CodeView/MergingTypeTableBuilder.cpp
+++ b/llvm/lib/DebugInfo/CodeView/MergingTypeTableBuilder.cpp
@@ -90,7 +90,9 @@ static inline ArrayRef<uint8_t> stabilize(BumpPtrAllocator &Alloc,
 TypeIndex MergingTypeTableBuilder::insertRecordAs(hash_code Hash,
                                                   ArrayRef<uint8_t> &Record) {
   assert(Record.size() < UINT32_MAX && "Record too big");
-  assert(Record.size() % 4 == 0 && "Record is not aligned to 4 bytes!");
+  assert(Record.size() % 4 == 0 &&
+         "The type record size is not a multiple of 4 bytes which will cause "
+         "misalignment in the output TPI stream!");
 
   LocallyHashedType WeakHash{Hash, Record};
   auto Result = HashedRecords.try_emplace(WeakHash, nextTypeIndex());
diff --git a/llvm/lib/DebugInfo/CodeView/TypeStreamMerger.cpp b/llvm/lib/DebugInfo/CodeView/TypeStreamMerger.cpp
index f9fca74a219..c233db5c1d0 100644
--- a/llvm/lib/DebugInfo/CodeView/TypeStreamMerger.cpp
+++ b/llvm/lib/DebugInfo/CodeView/TypeStreamMerger.cpp
@@ -360,16 +360,18 @@ Error TypeStreamMerger::remapType(const CVType &Type) {
         [this, Type](MutableArrayRef<uint8_t> Storage) -> ArrayRef<uint8_t> {
       return remapIndices(Type, Storage);
     };
+    unsigned AlignedSize = alignTo(Type.RecordData.size(), 4);
+
     if (LLVM_LIKELY(UseGlobalHashes)) {
       GlobalTypeTableBuilder &Dest =
           isIdRecord(Type.kind()) ? *DestGlobalIdStream : *DestGlobalTypeStream;
       GloballyHashedType H = GlobalHashes[CurIndex.toArrayIndex()];
-      DestIdx = Dest.insertRecordAs(H, Type.RecordData.size(), DoSerialize);
+      DestIdx = Dest.insertRecordAs(H, AlignedSize, DoSerialize);
     } else {
       MergingTypeTableBuilder &Dest =
           isIdRecord(Type.kind()) ? *DestIdStream : *DestTypeStream;
 
-      RemapStorage.resize(Type.RecordData.size());
+      RemapStorage.resize(AlignedSize);
       ArrayRef<uint8_t> Result = DoSerialize(RemapStorage);
       if (!Result.empty())
         DestIdx = Dest.insertRecordBytes(Result);
@@ -386,9 +388,15 @@ Error TypeStreamMerger::remapType(const CVType &Type) {
 ArrayRef<uint8_t>
 TypeStreamMerger::remapIndices(const CVType &OriginalType,
                                MutableArrayRef<uint8_t> Storage) {
+  unsigned Align = OriginalType.RecordData.size() & 3;
+  unsigned AlignedSize = alignTo(OriginalType.RecordData.size(), 4);
+  assert(Storage.size() == AlignedSize &&
+         "The storage buffer size is not a multiple of 4 bytes which will "
+         "cause misalignment in the output TPI stream!");
+
   SmallVector<TiReference, 4> Refs;
   discoverTypeIndices(OriginalType.RecordData, Refs);
-  if (Refs.empty())
+  if (Refs.empty() && Align == 0)
     return OriginalType.RecordData;
 
   ::memcpy(Storage.data(), OriginalType.RecordData.data(),
@@ -408,6 +416,16 @@ TypeStreamMerger::remapIndices(const CVType &OriginalType,
         return {};
     }
   }
+
+  if (Align > 0) {
+    RecordPrefix *StorageHeader =
+        reinterpret_cast<RecordPrefix *>(Storage.data());
+    StorageHeader->RecordLen += 4 - Align;
+
+    DestContent = Storage.data() + OriginalType.RecordData.size();
+    for (; Align < 4; ++Align)
+      *DestContent++ = LF_PAD4 - Align;
+  }
   return Storage;
 }
 
diff --git a/llvm/lib/DebugInfo/PDB/Native/TpiStreamBuilder.cpp b/llvm/lib/DebugInfo/PDB/Native/TpiStreamBuilder.cpp
index 4f10f8524a9..51a1f0a544e 100644
--- a/llvm/lib/DebugInfo/PDB/Native/TpiStreamBuilder.cpp
+++ b/llvm/lib/DebugInfo/PDB/Native/TpiStreamBuilder.cpp
@@ -44,6 +44,9 @@ void TpiStreamBuilder::setVersionHeader(PdbRaw_TpiVer Version) {
 void TpiStreamBuilder::addTypeRecord(ArrayRef<uint8_t> Record,
                                      Optional<uint32_t> Hash) {
   // If we just crossed an 8KB threshold, add a type index offset.
+  assert(((Record.size() & 3) == 0) &&
+         "The type record's size is not a multiple of 4 bytes which will "
+         "cause misalignment in the output TPI stream!");
   size_t NewSize = TypeRecordBytes + Record.size();
   constexpr size_t EightKB = 8 * 1024;
   if (NewSize / EightKB > TypeRecordBytes / EightKB || TypeRecords.empty()) {
@@ -153,8 +156,11 @@ Error TpiStreamBuilder::commit(const msf::MSFLayout &Layout,
     return EC;
 
   for (auto Rec : TypeRecords) {
-    assert(!Rec.empty()); // An empty record will not write anything, but it
-                          // would shift all offsets from here on.
+    assert(!Rec.empty() && "Attempting to write an empty type record shifts "
+                           "all offsets in the TPI stream!");
+    assert(((Rec.size() & 3) == 0) &&
+           "The type record's size is not a multiple of 4 bytes which will "
+           "cause misalignment in the output TPI stream!");
     if (auto EC = Writer.writeBytes(Rec))
       return EC;
   }