Parse: Concatenated string literals should be verified in inline asm

While we would correctly handle asm("foo") and reject asm(L"bar"), we
weren't careful to handle cases where an ascii literal could be
concatenated with a wide literal.

This fixes PR21822.

llvm-svn: 223992

4 files changed, 18 insertions, 29 deletions

diff --git a/clang/include/clang/Basic/DiagnosticSemaKinds.td b/clang/include/clang/Basic/DiagnosticSemaKinds.td
index 28ac96db91b..c78aba4c5da 100644
--- a/clang/include/clang/Basic/DiagnosticSemaKinds.td
+++ b/clang/include/clang/Basic/DiagnosticSemaKinds.td
@@ -6143,7 +6143,6 @@ def warn_cast_qual2 : Warning<"cast from %0 to %1 must have all intermediate "
 
 // inline asm.
 let CategoryName = "Inline Assembly Issue" in {
-  def err_asm_wide_character : Error<"wide string is invalid in 'asm'">;
   def err_asm_invalid_lvalue_in_output : Error<"invalid lvalue in asm output">;
   def err_asm_invalid_output_constraint : Error<
     "invalid output constraint '%0' in asm">;
diff --git a/clang/lib/Parse/Parser.cpp b/clang/lib/Parse/Parser.cpp
index 4ddc5bfdada..7119e9af760 100644
--- a/clang/lib/Parse/Parser.cpp
+++ b/clang/lib/Parse/Parser.cpp
@@ -1224,26 +1224,23 @@ void Parser::ParseKNRParamDeclarations(Declarator &D) {
 ///         string-literal
 ///
 ExprResult Parser::ParseAsmStringLiteral() {
-  switch (Tok.getKind()) {
-    case tok::string_literal:
-      break;
-    case tok::utf8_string_literal:
-    case tok::utf16_string_literal:
-    case tok::utf32_string_literal:
-    case tok::wide_string_literal: {
-      SourceLocation L = Tok.getLocation();
+  if (!isTokenStringLiteral()) {
+    Diag(Tok, diag::err_expected_string_literal)
+      << /*Source='in...'*/0 << "'asm'";
+    return ExprError();
+  }
+
+  ExprResult AsmString(ParseStringLiteralExpression());
+  if (!AsmString.isInvalid()) {
+    const auto *SL = cast<StringLiteral>(AsmString.get());
+    if (!SL->isAscii()) {
       Diag(Tok, diag::err_asm_operand_wide_string_literal)
-        << (Tok.getKind() == tok::wide_string_literal)
-        << SourceRange(L, L);
+        << SL->isWide()
+        << SL->getSourceRange();
       return ExprError();
     }
-    default:
-      Diag(Tok, diag::err_expected_string_literal)
-        << /*Source='in...'*/0 << "'asm'";
-      return ExprError();
   }
-
-  return ParseStringLiteralExpression();
+  return AsmString;
 }
 
 /// ParseSimpleAsm
diff --git a/clang/lib/Sema/SemaStmtAsm.cpp b/clang/lib/Sema/SemaStmtAsm.cpp
index a2e436ae7ee..e0f3dfe6e00 100644
--- a/clang/lib/Sema/SemaStmtAsm.cpp
+++ b/clang/lib/Sema/SemaStmtAsm.cpp
@@ -116,15 +116,11 @@ StmtResult Sema::ActOnGCCAsmStmt(SourceLocation AsmLoc, bool IsSimple,
   SmallVector<TargetInfo::ConstraintInfo, 4> OutputConstraintInfos;
 
   // The parser verifies that there is a string literal here.
-  if (!AsmString->isAscii())
-    return StmtError(Diag(AsmString->getLocStart(),diag::err_asm_wide_character)
-      << AsmString->getSourceRange());
+  assert(AsmString->isAscii());
 
   for (unsigned i = 0; i != NumOutputs; i++) {
     StringLiteral *Literal = Constraints[i];
-    if (!Literal->isAscii())
-      return StmtError(Diag(Literal->getLocStart(),diag::err_asm_wide_character)
-        << Literal->getSourceRange());
+    assert(Literal->isAscii());
 
     StringRef OutputName;
     if (Names[i])
@@ -172,9 +168,7 @@ StmtResult Sema::ActOnGCCAsmStmt(SourceLocation AsmLoc, bool IsSimple,
 
   for (unsigned i = NumOutputs, e = NumOutputs + NumInputs; i != e; i++) {
     StringLiteral *Literal = Constraints[i];
-    if (!Literal->isAscii())
-      return StmtError(Diag(Literal->getLocStart(),diag::err_asm_wide_character)
-        << Literal->getSourceRange());
+    assert(Literal->isAscii());
 
     StringRef InputName;
     if (Names[i])
@@ -240,9 +234,7 @@ StmtResult Sema::ActOnGCCAsmStmt(SourceLocation AsmLoc, bool IsSimple,
   // Check that the clobbers are valid.
   for (unsigned i = 0; i != NumClobbers; i++) {
     StringLiteral *Literal = Clobbers[i];
-    if (!Literal->isAscii())
-      return StmtError(Diag(Literal->getLocStart(),diag::err_asm_wide_character)
-        << Literal->getSourceRange());
+    assert(Literal->isAscii());
 
     StringRef Clobber = Literal->getString();
 
diff --git a/clang/test/Parser/asm.cpp b/clang/test/Parser/asm.cpp
index 35a497c83a1..9f64dfea476 100644
--- a/clang/test/Parser/asm.cpp
+++ b/clang/test/Parser/asm.cpp
@@ -6,3 +6,4 @@ int foo3 asm (u8"bar3"); // expected-error {{cannot use unicode string literal i
 int foo4 asm (u"bar4"); // expected-error {{cannot use unicode string literal in 'asm'}}
 int foo5 asm (U"bar5"); // expected-error {{cannot use unicode string literal in 'asm'}}
 int foo6 asm ("bar6"_x); // expected-error {{string literal with user-defined suffix cannot be used here}}
+int foo6 asm ("" L"bar7"); // expected-error {{cannot use wide string literal in 'asm'}}