[clang][bytecode] Handle __builtin_wcslen

[tbaederr]

Handle different char widths in builtin_strlen.

[llvmbot]

@llvm/pr-subscribers-clang

Author: Timm Baeder (tbaederr)

Changes

Handle different char widths in builtin_strlen.

---

Full diff: https://github.com/llvm/llvm-project/pull/119187.diff

2 Files Affected:

• (modified) clang/lib/AST/ByteCode/InterpBuiltin.cpp (+18-3)
• (modified) clang/test/AST/ByteCode/builtin-functions.cpp (+12)

diff --git a/clang/lib/AST/ByteCode/InterpBuiltin.cpp b/clang/lib/AST/ByteCode/InterpBuiltin.cpp
index 24b630d0455e14..df5b4fcb3f0fbb 100644
--- a/clang/lib/AST/ByteCode/InterpBuiltin.cpp
+++ b/clang/lib/AST/ByteCode/InterpBuiltin.cpp
@@ -243,7 +243,7 @@ static bool interp__builtin_strlen(InterpState &S, CodePtr OpPC,
   unsigned ID = Func->getBuiltinID();
   const Pointer &StrPtr = getParam<Pointer>(Frame, 0);
 
-  if (ID == Builtin::BIstrlen)
+  if (ID == Builtin::BIstrlen || ID == Builtin::BIwcslen)
     diagnoseNonConstexprBuiltin(S, OpPC, ID);
 
   if (!CheckArray(S, OpPC, StrPtr))
@@ -256,7 +256,7 @@ static bool interp__builtin_strlen(InterpState &S, CodePtr OpPC,
     return false;
 
   assert(StrPtr.getFieldDesc()->isPrimitiveArray());
-
+  unsigned ElemSize = StrPtr.getFieldDesc()->getElemSize();
   size_t Len = 0;
   for (size_t I = StrPtr.getIndex();; ++I, ++Len) {
     const Pointer &ElemPtr = StrPtr.atIndex(I);
@@ -264,7 +264,20 @@ static bool interp__builtin_strlen(InterpState &S, CodePtr OpPC,
     if (!CheckRange(S, OpPC, ElemPtr, AK_Read))
       return false;
 
-    uint8_t Val = ElemPtr.deref<uint8_t>();
+    uint32_t Val;
+    switch (ElemSize) {
+    case 1:
+      Val = ElemPtr.deref<uint8_t>();
+      break;
+    case 2:
+      Val = ElemPtr.deref<uint16_t>();
+      break;
+    case 4:
+      Val = ElemPtr.deref<uint32_t>();
+      break;
+    default:
+      llvm_unreachable("Unsupported char size");
+    }
     if (Val == 0)
       break;
   }
@@ -1859,6 +1872,8 @@ bool InterpretBuiltin(InterpState &S, CodePtr OpPC, const Function *F,
     break;
   case Builtin::BI__builtin_strlen:
   case Builtin::BIstrlen:
+  case Builtin::BI__builtin_wcslen:
+  case Builtin::BIwcslen:
     if (!interp__builtin_strlen(S, OpPC, Frame, F, Call))
       return false;
     break;
diff --git a/clang/test/AST/ByteCode/builtin-functions.cpp b/clang/test/AST/ByteCode/builtin-functions.cpp
index e2121a54e15768..4c21496d3972c9 100644
--- a/clang/test/AST/ByteCode/builtin-functions.cpp
+++ b/clang/test/AST/ByteCode/builtin-functions.cpp
@@ -15,6 +15,10 @@
 #error "huh?"
 #endif
 
+extern "C" {
+  typedef decltype(sizeof(int)) size_t;
+  extern size_t wcslen(const wchar_t *p);
+}
 
 namespace strcmp {
   constexpr char kFoobar[6] = {'f','o','o','b','a','r'};
@@ -93,6 +97,14 @@ constexpr const char *a = "foo\0quux";
   constexpr char d[] = { 'f', 'o', 'o' }; // no nul terminator.
   constexpr int bad = __builtin_strlen(d); // both-error {{constant expression}} \
                                            // both-note {{one-past-the-end}}
+
+  constexpr int wn = __builtin_wcslen(L"hello");
+  static_assert(wn == 5);
+  constexpr int wm = wcslen(L"hello"); // both-error {{constant expression}} \
+                                       // both-note {{non-constexpr function 'wcslen' cannot be used in a constant expression}}
+
+  int arr[3]; // both-note {{here}}
+  int wk = arr[wcslen(L"hello")]; // both-warning {{array index 5}}
 }
 
 namespace nan {

[cor3ntin]

LGTM modulo comment

[cor3ntin]

Should we assert that if ID == Builtin::BIwcslen ElemSize is the size of wchar_t?

[tbaederr]

Done