[TBAA] Handle bitfields when generating !tbaa.struct metadata. (llvm#82922)

At the moment, clang generates what I believe are incorrect !tbaa.struct
fields for named bitfields. At the moment, the base type size is used
for named bifields (e.g. sizeof(int)) instead of the bifield width per
field. This results in overalpping fields in !tbaa.struct metadata.

This causes incorrect results when extracting individual copied fields
from !tbaa.struct as in added in dc85719.

This patch fixes that by skipping by combining adjacent bitfields
in fields with correct sizes.

Fixes llvm#82586

(cherry-picked from d2a9df2)

Author: fhahn

clang/lib/CodeGen/CodeGenModule.cpp

@@ -393,8 +393,8 @@ CodeGenModule::CodeGenModule(ASTContext &C,
   // Enable TBAA unless it's suppressed. ThreadSanitizer needs TBAA even at O0.
   if (LangOpts.Sanitize.has(SanitizerKind::Thread) ||
       (!CodeGenOpts.RelaxedAliasing && CodeGenOpts.OptimizationLevel > 0))
-    TBAA.reset(new CodeGenTBAA(Context, TheModule, CodeGenOpts, getLangOpts(),
-                               getCXXABI().getMangleContext()));
+    TBAA.reset(new CodeGenTBAA(Context, getTypes(), TheModule, CodeGenOpts,
+                               getLangOpts(), getCXXABI().getMangleContext()));
 
   // If debug info or coverage generation is enabled, create the CGDebugInfo
   // object.

clang/lib/CodeGen/CodeGenTBAA.cpp

@@ -15,6 +15,8 @@
 //===----------------------------------------------------------------------===//
 
 #include "CodeGenTBAA.h"
+#include "CGRecordLayout.h"
+#include "CodeGenTypes.h"
 #include "clang/AST/ASTContext.h"
 #include "clang/AST/Attr.h"
 #include "clang/AST/Mangle.h"
@@ -26,16 +28,16 @@
 #include "llvm/IR/Metadata.h"
 #include "llvm/IR/Module.h"
 #include "llvm/IR/Type.h"
+#include "llvm/Support/Debug.h"
 using namespace clang;
 using namespace CodeGen;
 
-CodeGenTBAA::CodeGenTBAA(ASTContext &Ctx, llvm::Module &M,
-                         const CodeGenOptions &CGO,
+CodeGenTBAA::CodeGenTBAA(ASTContext &Ctx, CodeGenTypes &CGTypes,
+                         llvm::Module &M, const CodeGenOptions &CGO,
                          const LangOptions &Features, MangleContext &MContext)
-  : Context(Ctx), Module(M), CodeGenOpts(CGO),
-    Features(Features), MContext(MContext), MDHelper(M.getContext()),
-    Root(nullptr), Char(nullptr)
-{}
+    : Context(Ctx), CGTypes(CGTypes), Module(M), CodeGenOpts(CGO),
+      Features(Features), MContext(MContext), MDHelper(M.getContext()),
+      Root(nullptr), Char(nullptr) {}
 
 CodeGenTBAA::~CodeGenTBAA() {
 }
@@ -291,14 +293,34 @@ CodeGenTBAA::CollectFields(uint64_t BaseOffset,
         return false;
 
     const ASTRecordLayout &Layout = Context.getASTRecordLayout(RD);
+    const CGRecordLayout &CGRL = CGTypes.getCGRecordLayout(RD);
 
     unsigned idx = 0;
-    for (RecordDecl::field_iterator i = RD->field_begin(),
-         e = RD->field_end(); i != e; ++i, ++idx) {
-      if ((*i)->isZeroSize(Context) || (*i)->isUnnamedBitfield())
+    for (RecordDecl::field_iterator i = RD->field_begin(), e = RD->field_end();
+         i != e; ++i, ++idx) {
+      if ((*i)->isZeroSize(Context))
         continue;
-      uint64_t Offset = BaseOffset +
-                        Layout.getFieldOffset(idx) / Context.getCharWidth();
+
+      uint64_t Offset =
+          BaseOffset + Layout.getFieldOffset(idx) / Context.getCharWidth();
+
+      // Create a single field for consecutive named bitfields using char as
+      // base type.
+      if ((*i)->isBitField()) {
+        const CGBitFieldInfo &Info = CGRL.getBitFieldInfo(*i);
+        if (Info.Offset != 0)
+          continue;
+        unsigned CurrentBitFieldSize = Info.StorageSize;
+        uint64_t Size =
+            llvm::divideCeil(CurrentBitFieldSize, Context.getCharWidth());
+        llvm::MDNode *TBAAType = getChar();
+        llvm::MDNode *TBAATag =
+            getAccessTagInfo(TBAAAccessInfo(TBAAType, Size));
+        Fields.push_back(
+            llvm::MDBuilder::TBAAStructField(Offset, Size, TBAATag));
+        continue;
+      }
+
       QualType FieldQTy = i->getType();
       if (!CollectFields(Offset, FieldQTy, Fields,
                          MayAlias || TypeHasMayAlias(FieldQTy)))

clang/lib/CodeGen/CodeGenTBAA.h

@@ -29,6 +29,7 @@ namespace clang {
   class Type;
 
 namespace CodeGen {
+class CodeGenTypes;
 
 // TBAAAccessKind - A kind of TBAA memory access descriptor.
 enum class TBAAAccessKind : unsigned {
@@ -115,6 +116,7 @@ struct TBAAAccessInfo {
 /// while lowering AST types to LLVM types.
 class CodeGenTBAA {
   ASTContext &Context;
+  CodeGenTypes &CGTypes;
   llvm::Module &Module;
   const CodeGenOptions &CodeGenOpts;
   const LangOptions &Features;
@@ -167,8 +169,9 @@ class CodeGenTBAA {
   llvm::MDNode *getBaseTypeInfoHelper(const Type *Ty);
 
 public:
-  CodeGenTBAA(ASTContext &Ctx, llvm::Module &M, const CodeGenOptions &CGO,
-              const LangOptions &Features, MangleContext &MContext);
+  CodeGenTBAA(ASTContext &Ctx, CodeGenTypes &CGTypes, llvm::Module &M,
+              const CodeGenOptions &CGO, const LangOptions &Features,
+              MangleContext &MContext);
   ~CodeGenTBAA();
 
   /// getTypeInfo - Get metadata used to describe accesses to objects of the

clang/test/CodeGen/tbaa-struct.cpp

@@ -162,11 +162,11 @@ void copy10(NamedBitfields3 *a1, NamedBitfields3 *a2) {
 // CHECK-OLD: [[TS3]] = !{i64 0, i64 8, !{{.*}}, i64 0, i64 2, !{{.*}}, i64 4, i64 8, !{{.*}}}
 // CHECK-OLD: [[TS4]] = !{i64 0, i64 1, [[TAG_CHAR]], i64 1, i64 1, [[TAG_CHAR]], i64 2, i64 1, [[TAG_CHAR]]}
 // CHECK-OLD: [[TS5]] = !{i64 0, i64 1, [[TAG_CHAR]], i64 4, i64 1, [[TAG_CHAR]], i64 5, i64 1, [[TAG_CHAR]]}
-// CHECK-OLD: [[TS6]] = !{i64 0, i64 4, [[TAG_INT]], i64 1, i64 4, [[TAG_INT]], i64 2, i64 1, [[TAG_CHAR]], i64 8, i64 8, [[TAG_DOUBLE:!.+]]}
+// CHECK-OLD: [[TS6]] = !{i64 0, i64 2, [[TAG_CHAR]], i64 2, i64 1, [[TAG_CHAR]], i64 8, i64 8, [[TAG_DOUBLE:!.+]]}
 // CHECK-OLD: [[TAG_DOUBLE]] = !{[[DOUBLE:!.+]], [[DOUBLE]], i64 0}
 // CHECK-OLD  [[DOUBLE]] = !{!"double", [[CHAR]], i64 0}
-// CHECK-OLD: [[TS7]] = !{i64 0, i64 1, [[TAG_CHAR]], i64 1, i64 1, [[TAG_CHAR]], i64 2, i64 1, [[TAG_CHAR]], i64 3, i64 4, [[TAG_INT]], i64 3, i64 4, [[TAG_INT]], i64 4, i64 1, [[TAG_CHAR]], i64 8, i64 8, [[TAG_DOUBLE]], i64 16, i64 4, [[TAG_INT]]}
-// CHECK-OLD: [[TS8]] = !{i64 1, i64 4, [[TAG_INT]], i64 2, i64 4, [[TAG_INT]], i64 8, i64 8, [[TAG_DOUBLE]]}
+// CHECK-OLD: [[TS7]] = !{i64 0, i64 1, [[TAG_CHAR]], i64 1, i64 1, [[TAG_CHAR]], i64 2, i64 1, [[TAG_CHAR]], i64 3, i64 1, [[TAG_CHAR]], i64 4, i64 1, [[TAG_CHAR]], i64 8, i64 8, [[TAG_DOUBLE]], i64 16, i64 1, [[TAG_CHAR]]}
+// CHECK-OLD: [[TS8]] = !{i64 0, i64 4, [[TAG_CHAR]], i64 8, i64 8, [[TAG_DOUBLE]]}
 
 // CHECK-NEW-DAG: [[TYPE_char:!.*]] = !{{{.*}}, i64 1, !"omnipotent char"}
 // CHECK-NEW-DAG: [[TAG_char]] = !{[[TYPE_char]], [[TYPE_char]], i64 0, i64 0}