[clang] Fix underlying type of EmbedExpr (#99050)

Summary:
This patch makes remaining cases of #embed to emit int type since there
is an agreement to do that for C. C++ is being discussed, but in general
we don't want to produce different types for C and C++.

Test Plan: 

Reviewers: 

Subscribers: 

Tasks: 

Tags: 


Differential Revision: https://phabricator.intern.facebook.com/D60251342

Author: Fznamznon

clang/lib/AST/Expr.cpp

@@ -2376,7 +2376,7 @@ APValue SourceLocExpr::EvaluateInContext(const ASTContext &Ctx,
 EmbedExpr::EmbedExpr(const ASTContext &Ctx, SourceLocation Loc,
                      EmbedDataStorage *Data, unsigned Begin,
                      unsigned NumOfElements)
-    : Expr(EmbedExprClass, Ctx.UnsignedCharTy, VK_PRValue, OK_Ordinary),
+    : Expr(EmbedExprClass, Ctx.IntTy, VK_PRValue, OK_Ordinary),
       EmbedKeywordLoc(Loc), Ctx(&Ctx), Data(Data), Begin(Begin),
       NumOfElements(NumOfElements) {
   setDependence(ExprDependence::None);

clang/lib/Sema/SemaInit.cpp

@@ -2016,7 +2016,7 @@ canInitializeArrayWithEmbedDataString(ArrayRef<Expr *> ExprList,
   if (InitType->isArrayType()) {
     const ArrayType *InitArrayType = InitType->getAsArrayTypeUnsafe();
     QualType InitElementTy = InitArrayType->getElementType();
-    QualType EmbedExprElementTy = EE->getType();
+    QualType EmbedExprElementTy = EE->getDataStringLiteral()->getType();
     const bool TypesMatch =
         Context.typesAreCompatible(InitElementTy, EmbedExprElementTy) ||
         (InitElementTy->isCharType() && EmbedExprElementTy->isCharType());

clang/test/Preprocessor/Inputs/big_char.txt

@@ -0,0 +1 @@
+�

clang/test/Preprocessor/embed_codegen.cpp

@@ -14,9 +14,9 @@ int ca[] = {
 };
 
 // CHECK: %arrayinit.element = getelementptr inbounds i32, ptr %notca, i64 1
-// CHECK: store i8 106, ptr %arrayinit.element, align 4
+// CHECK: store i32 106, ptr %arrayinit.element, align 4
 // CHECK: %arrayinit.element1 = getelementptr inbounds i32, ptr %notca, i64 2
-// CHECK: store i8 107, ptr %arrayinit.element1, align 4
+// CHECK: store i32 107, ptr %arrayinit.element1, align 4
 int notca[] = {
 a
 #embed <jk.txt> prefix(,)
@@ -75,9 +75,9 @@ constexpr struct T t[] = {
 // CHECK:  %arrayinit.element7 = getelementptr inbounds %struct.T, ptr %tnonc, i64 1
 // CHECK:  call void @llvm.memset.p0.i64(ptr align 4 %arrayinit.element7, i8 0, i64 20, i1 false)
 // CHECK:  %arr8 = getelementptr inbounds %struct.T, ptr %arrayinit.element7, i32 0, i32 0
-// CHECK:  store i8 106, ptr %arr8, align 4
+// CHECK:  store i32 106, ptr %arr8, align 4
 // CHECK:  %arrayinit.element9 = getelementptr inbounds i32, ptr %arr8, i64 1
-// CHECK:  store i8 107, ptr %arrayinit.element9, align 4
+// CHECK:  store i32 107, ptr %arrayinit.element9, align 4
 struct T tnonc[] = {
   a, 300, 1, 2, 3
 #embed <jk.txt> prefix(,)

clang/test/Preprocessor/embed_weird.cpp

@@ -115,3 +115,14 @@ void f1() {
   };
 }
 #endif
+
+struct HasChar {
+  signed char ch;
+};
+
+constexpr struct HasChar c = {
+#embed "Inputs/big_char.txt" // cxx-error {{constant expression evaluates to 255 which cannot be narrowed to type 'signed char'}} \
+                                cxx-note {{insert an explicit cast to silence this issue}} \
+                                c-error {{constexpr initializer evaluates to 255 which is not exactly representable in type 'signed char'}}
+
+};