[clang] [TBAA] Generate tbaa.struct single field with char tag for unions. (PR #84370)

[Florian Hahn via cfe-commits]

https://github.com/fhahn created https://github.com/llvm/llvm-project/pull/84370

At the moment,distinct fields for each union member are generated. When copying a union, we don't know which union member is active, so there's no benefit from recording the different fields. It can result in converting tbaa.struct fields to incorrect tbaa nodes when extracting fields.

>From 379844ae4a78d13ca80a12ee34338a53723ffab4 Mon Sep 17 00:00:00 2001
From: Florian Hahn <flo at fhahn.com>
Date: Thu, 7 Mar 2024 16:28:00 +0000
Subject: [PATCH] [TBAA] Generate tbaa.struct single field with char tag for
 unions.

At the moment,distinct fields for each union member are generated. When
copying a union, we don't know which union member is active, so there's
no benefit from recording the different fields. It can also result in
converting tbaa.struct fields to incorrect tbaa nodes when extracting
fields.
---
 clang/lib/CodeGen/CodeGenTBAA.cpp  | 8 ++++++++
 clang/test/CodeGen/tbaa-struct.cpp | 8 +++-----
 2 files changed, 11 insertions(+), 5 deletions(-)

diff --git a/clang/lib/CodeGen/CodeGenTBAA.cpp b/clang/lib/CodeGen/CodeGenTBAA.cpp
index 8a081612193978..69fb1e11edc7dc 100644
--- a/clang/lib/CodeGen/CodeGenTBAA.cpp
+++ b/clang/lib/CodeGen/CodeGenTBAA.cpp
@@ -286,6 +286,14 @@ CodeGenTBAA::CollectFields(uint64_t BaseOffset,
   /* Things not handled yet include: C++ base classes, bitfields, */
 
   if (const RecordType *TTy = QTy->getAs<RecordType>()) {
+    if (TTy->isUnionType()) {
+      uint64_t Size = Context.getTypeSizeInChars(QTy).getQuantity();
+      llvm::MDNode *TBAAType = getChar();
+      llvm::MDNode *TBAATag = getAccessTagInfo(TBAAAccessInfo(TBAAType, Size));
+      Fields.push_back(
+          llvm::MDBuilder::TBAAStructField(BaseOffset, Size, TBAATag));
+      return true;
+    }
     const RecordDecl *RD = TTy->getDecl()->getDefinition();
     if (RD->hasFlexibleArrayMember())
       return false;
diff --git a/clang/test/CodeGen/tbaa-struct.cpp b/clang/test/CodeGen/tbaa-struct.cpp
index 63e4097946448e..9b4b7415142d93 100644
--- a/clang/test/CodeGen/tbaa-struct.cpp
+++ b/clang/test/CodeGen/tbaa-struct.cpp
@@ -191,7 +191,7 @@ void copy12(UnionMember2 *a1, UnionMember2 *a2) {
 // (offset, size) = (0,1) char; (4,2) short; (8,4) int; (12,1) char; (16,4) int; (20,4) int
 // CHECK-OLD: [[TS2]] = !{i64 0, i64 1, !{{.*}}, i64 4, i64 2, !{{.*}}, i64 8, i64 4, !{{.*}}, i64 12, i64 1, !{{.*}}, i64 16, i64 4, {{.*}}, i64 20, i64 4, {{.*}}}
 // (offset, size) = (0,8) char; (0,2) char; (4,8) char
-// CHECK-OLD: [[TS3]] = !{i64 0, i64 8, !{{.*}}, i64 0, i64 2, !{{.*}}, i64 4, i64 8, !{{.*}}}
+// CHECK-OLD: [[TS3]] = !{i64 0, i64 12, [[TAG_CHAR]]}
 // 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 2, [[TAG_CHAR]], i64 2, i64 1, [[TAG_CHAR]], i64 8, i64 8, [[TAG_DOUBLE:!.+]]}
@@ -199,10 +199,8 @@ void copy12(UnionMember2 *a1, UnionMember2 *a2) {
 // 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 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-OLD: [[TS9]] = !{i64 0, i64 8, [[TAG_DOUBLE]], i64 0, i64 4, [[TAG_FLOAT:!.+]], i64 8, i64 4, [[TAG_INT]]}
-// CHECK-OLD: [[TAG_FLOAT]]  = !{[[FLOAT:!.+]], [[FLOAT]], i64 0}
-// CHECK-OLD: [[FLOAT]] = !{!"float", [[CHAR]], i64 0}
-// CHECK-OLD: [[TS10]] = !{i64 0, i64 4, [[TAG_INT]], i64 8, i64 8, [[TAG_DOUBLE]], i64 8, i64 4, [[TAG_FLOAT:!.+]]}
+// CHECK-OLD: [[TS9]] = !{i64 0, i64 8, [[TAG_CHAR]], i64 8, i64 4, [[TAG_INT]]}
+// CHECK-OLD: [[TS10]] = !{i64 0, i64 4, [[TAG_INT]], i64 8, i64 8, [[TAG_CHAR]]}
 
 // CHECK-NEW-DAG: [[TYPE_char:!.*]] = !{{{.*}}, i64 1, !"omnipotent char"}
 // CHECK-NEW-DAG: [[TAG_char]] = !{[[TYPE_char]], [[TYPE_char]], i64 0, i64 0}