[clang][bytecode] Implement __builtin_constant_p (#130143)

tbaederr · web-flow · commit d08cf7900d2a · 2025-03-08T06:06:14.000+01:00
Use the regular code paths for interpreting.

Add new instructions: `StartSpeculation` will reset the diagnostics
pointers to `nullptr`, which will keep us from reporting any diagnostics
during speculation. `EndSpeculation` will undo this.

The rest depends on what `Emitter` we use.

For `EvalEmitter`, we have no bytecode, so we implement `speculate()` by
simply visiting the first argument of `__builtin_constant_p`. If the
evaluation fails, we push a `0` on the stack, otherwise a `1`.

For `ByteCodeEmitter`, add another instrucion called `BCP`, that
interprets all the instructions following it until the next
`EndSpeculation` instruction. If any of those instructions fails, we
jump to the `EndLabel`, which brings us right before the
`EndSpeculation`. We then push the result on the stack.
diff --git a/clang/lib/AST/ByteCode/ByteCodeEmitter.cpp b/clang/lib/AST/ByteCode/ByteCodeEmitter.cpp
@@ -367,6 +367,16 @@ bool ByteCodeEmitter::fallthrough(const LabelTy &Label) {
   return true;
 }
 
+bool ByteCodeEmitter::speculate(const CallExpr *E, const LabelTy &EndLabel) {
+  const Expr *Arg = E->getArg(0);
+  PrimType T = Ctx.classify(Arg->getType()).value_or(PT_Ptr);
+  if (!this->emitBCP(getOffset(EndLabel), T, E))
+    return false;
+  if (!this->visit(Arg))
+    return false;
+  return true;
+}
+
 //===----------------------------------------------------------------------===//
 // Opcode emitters
 //===----------------------------------------------------------------------===//
diff --git a/clang/lib/AST/ByteCode/ByteCodeEmitter.h b/clang/lib/AST/ByteCode/ByteCodeEmitter.h
@@ -48,12 +48,16 @@ class ByteCodeEmitter {
   virtual bool visitFunc(const FunctionDecl *E) = 0;
   virtual bool visitExpr(const Expr *E, bool DestroyToplevelScope) = 0;
   virtual bool visitDeclAndReturn(const VarDecl *E, bool ConstantContext) = 0;
+  virtual bool visit(const Expr *E) = 0;
+  virtual bool emitBool(bool V, const Expr *E) = 0;
 
   /// Emits jumps.
   bool jumpTrue(const LabelTy &Label);
   bool jumpFalse(const LabelTy &Label);
   bool jump(const LabelTy &Label);
   bool fallthrough(const LabelTy &Label);
+  /// Speculative execution.
+  bool speculate(const CallExpr *E, const LabelTy &EndLabel);
 
   /// We're always emitting bytecode.
   bool isActive() const { return true; }
diff --git a/clang/lib/AST/ByteCode/Compiler.cpp b/clang/lib/AST/ByteCode/Compiler.cpp
@@ -4681,6 +4681,28 @@ bool Compiler<Emitter>::visitAPValueInitializer(const APValue &Val,
 template <class Emitter>
 bool Compiler<Emitter>::VisitBuiltinCallExpr(const CallExpr *E,
                                              unsigned BuiltinID) {
+
+  if (BuiltinID == Builtin::BI__builtin_constant_p) {
+    // Void argument is always invalid and harder to handle later.
+    if (E->getArg(0)->getType()->isVoidType()) {
+      if (DiscardResult)
+        return true;
+      return this->emitConst(0, E);
+    }
+
+    if (!this->emitStartSpeculation(E))
+      return false;
+    LabelTy EndLabel = this->getLabel();
+    if (!this->speculate(E, EndLabel))
+      return false;
+    this->fallthrough(EndLabel);
+    if (!this->emitEndSpeculation(E))
+      return false;
+    if (DiscardResult)
+      return this->emitPop(classifyPrim(E), E);
+    return true;
+  }
+
   const Function *Func = getFunction(E->getDirectCallee());
   if (!Func)
     return false;
diff --git a/clang/lib/AST/ByteCode/Compiler.h b/clang/lib/AST/ByteCode/Compiler.h
@@ -274,7 +274,7 @@ class Compiler : public ConstStmtVisitor<Compiler<Emitter>, bool>,
   /// Evaluates an expression and places the result on the stack. If the
   /// expression is of composite type, a local variable will be created
   /// and a pointer to said variable will be placed on the stack.
-  bool visit(const Expr *E);
+  bool visit(const Expr *E) override;
   /// Compiles an initializer. This is like visit() but it will never
   /// create a variable and instead rely on a variable already having
   /// been created. visitInitializer() then relies on a pointer to this
@@ -342,6 +342,9 @@ class Compiler : public ConstStmtVisitor<Compiler<Emitter>, bool>,
   /// Emits an integer constant.
   template <typename T> bool emitConst(T Value, PrimType Ty, const Expr *E);
   template <typename T> bool emitConst(T Value, const Expr *E);
+  bool emitBool(bool V, const Expr *E) override {
+    return this->emitConst(V, E);
+  }
 
   llvm::RoundingMode getRoundingMode(const Expr *E) const {
     FPOptions FPO = E->getFPFeaturesInEffect(Ctx.getLangOpts());
diff --git a/clang/lib/AST/ByteCode/EvalEmitter.cpp b/clang/lib/AST/ByteCode/EvalEmitter.cpp
@@ -127,6 +127,33 @@ bool EvalEmitter::fallthrough(const LabelTy &Label) {
   return true;
 }
 
+bool EvalEmitter::speculate(const CallExpr *E, const LabelTy &EndLabel) {
+  size_t StackSizeBefore = S.Stk.size();
+  const Expr *Arg = E->getArg(0);
+  if (!this->visit(Arg)) {
+    S.Stk.clearTo(StackSizeBefore);
+
+    if (S.inConstantContext() || Arg->HasSideEffects(S.getASTContext()))
+      return this->emitBool(false, E);
+    return Invalid(S, OpPC);
+  }
+
+  PrimType T = Ctx.classify(Arg->getType()).value_or(PT_Ptr);
+  if (T == PT_Ptr) {
+    const auto &Ptr = S.Stk.pop<Pointer>();
+    return this->emitBool(CheckBCPResult(S, Ptr), E);
+  } else if (T == PT_FnPtr) {
+    S.Stk.discard<FunctionPointer>();
+    // Never accepted
+    return this->emitBool(false, E);
+  }
+
+  // Otherwise, this is fine!
+  if (!this->emitPop(T, E))
+    return false;
+  return this->emitBool(true, E);
+}
+
 template <PrimType OpType> bool EvalEmitter::emitRet(const SourceInfo &Info) {
   if (!isActive())
     return true;
diff --git a/clang/lib/AST/ByteCode/EvalEmitter.h b/clang/lib/AST/ByteCode/EvalEmitter.h
@@ -55,12 +55,16 @@ class EvalEmitter : public SourceMapper {
   virtual bool visitExpr(const Expr *E, bool DestroyToplevelScope) = 0;
   virtual bool visitDeclAndReturn(const VarDecl *VD, bool ConstantContext) = 0;
   virtual bool visitFunc(const FunctionDecl *F) = 0;
+  virtual bool visit(const Expr *E) = 0;
+  virtual bool emitBool(bool V, const Expr *E) = 0;
 
   /// Emits jumps.
   bool jumpTrue(const LabelTy &Label);
   bool jumpFalse(const LabelTy &Label);
   bool jump(const LabelTy &Label);
   bool fallthrough(const LabelTy &Label);
+  /// Speculative execution.
+  bool speculate(const CallExpr *E, const LabelTy &EndLabel);
 
   /// Since expressions can only jump forward, predicated execution is
   /// used to deal with if-else statements.
diff --git a/clang/lib/AST/ByteCode/Interp.cpp b/clang/lib/AST/ByteCode/Interp.cpp
@@ -54,6 +54,79 @@ static bool Jf(InterpState &S, CodePtr &PC, int32_t Offset) {
   return true;
 }
 
+// https://github.com/llvm/llvm-project/issues/102513
+#if defined(_MSC_VER) && !defined(__clang__) && !defined(NDEBUG)
+#pragma optimize("", off)
+#endif
+// FIXME: We have the large switch over all opcodes here again, and in
+// Interpret().
+static bool BCP(InterpState &S, CodePtr &RealPC, int32_t Offset, PrimType PT) {
+  [[maybe_unused]] CodePtr PCBefore = RealPC;
+  size_t StackSizeBefore = S.Stk.size();
+
+  auto SpeculativeInterp = [&S, RealPC]() -> bool {
+    const InterpFrame *StartFrame = S.Current;
+    CodePtr PC = RealPC;
+
+    for (;;) {
+      auto Op = PC.read<Opcode>();
+      if (Op == OP_EndSpeculation)
+        return true;
+      CodePtr OpPC = PC;
+
+      switch (Op) {
+#define GET_INTERP
+#include "Opcodes.inc"
+#undef GET_INTERP
+      }
+    }
+    llvm_unreachable("We didn't see an EndSpeculation op?");
+  };
+
+  if (SpeculativeInterp()) {
+    if (PT == PT_Ptr) {
+      const auto &Ptr = S.Stk.pop<Pointer>();
+      assert(S.Stk.size() == StackSizeBefore);
+      S.Stk.push<Integral<32, true>>(
+          Integral<32, true>::from(CheckBCPResult(S, Ptr)));
+    } else if (PT == PT_FnPtr) {
+      S.Stk.discard<FunctionPointer>();
+      S.Stk.push<Integral<32, true>>(Integral<32, true>::from(0));
+    } else {
+      // Pop the result from the stack and return success.
+      TYPE_SWITCH(PT, S.Stk.pop<T>(););
+      assert(S.Stk.size() == StackSizeBefore);
+      S.Stk.push<Integral<32, true>>(Integral<32, true>::from(1));
+    }
+  } else {
+    if (!S.inConstantContext())
+      return Invalid(S, RealPC);
+
+    S.Stk.clearTo(StackSizeBefore);
+    S.Stk.push<Integral<32, true>>(Integral<32, true>::from(0));
+  }
+
+  // RealPC should not have been modified.
+  assert(*RealPC == *PCBefore);
+
+  // Jump to end label. This is a little tricker than just RealPC += Offset
+  // because our usual jump instructions don't have any arguments, to the offset
+  // we get is a little too much and we need to subtract the size of the
+  // bool and PrimType arguments again.
+  int32_t ParamSize = align(sizeof(PrimType));
+  assert(Offset >= ParamSize);
+  RealPC += Offset - ParamSize;
+
+  [[maybe_unused]] CodePtr PCCopy = RealPC;
+  assert(PCCopy.read<Opcode>() == OP_EndSpeculation);
+
+  return true;
+}
+// https://github.com/llvm/llvm-project/issues/102513
+#if defined(_MSC_VER) && !defined(__clang__) && !defined(NDEBUG)
+#pragma optimize("", on)
+#endif
+
 static void diagnoseMissingInitializer(InterpState &S, CodePtr OpPC,
                                        const ValueDecl *VD) {
   const SourceInfo &E = S.Current->getSource(OpPC);
@@ -290,6 +363,22 @@ void cleanupAfterFunctionCall(InterpState &S, CodePtr OpPC,
     TYPE_SWITCH(Ty, S.Stk.discard<T>());
 }
 
+bool CheckBCPResult(InterpState &S, const Pointer &Ptr) {
+  if (Ptr.isDummy())
+    return false;
+  if (Ptr.isZero())
+    return true;
+  if (Ptr.isIntegralPointer())
+    return true;
+  if (Ptr.isTypeidPointer())
+    return true;
+
+  if (const Expr *Base = Ptr.getDeclDesc()->asExpr())
+    return isa<StringLiteral>(Base);
+
+  return false;
+}
+
 bool CheckExtern(InterpState &S, CodePtr OpPC, const Pointer &Ptr) {
   if (!Ptr.isExtern())
     return true;
diff --git a/clang/lib/AST/ByteCode/Interp.h b/clang/lib/AST/ByteCode/Interp.h
@@ -159,6 +159,7 @@ bool CheckLiteralType(InterpState &S, CodePtr OpPC, const Type *T);
 bool InvalidShuffleVectorIndex(InterpState &S, CodePtr OpPC, uint32_t Index);
 bool CheckBitCast(InterpState &S, CodePtr OpPC, bool HasIndeterminateBits,
                   bool TargetIsUCharOrByte);
+bool CheckBCPResult(InterpState &S, const Pointer &Ptr);
 
 template <typename T>
 static bool handleOverflow(InterpState &S, CodePtr OpPC, const T &SrcValue) {
@@ -2776,8 +2777,29 @@ inline bool Unsupported(InterpState &S, CodePtr OpPC) {
   return false;
 }
 
+inline bool StartSpeculation(InterpState &S, CodePtr OpPC) {
+  ++S.SpeculationDepth;
+  if (S.SpeculationDepth != 1)
+    return true;
+
+  assert(S.PrevDiags == nullptr);
+  S.PrevDiags = S.getEvalStatus().Diag;
+  S.getEvalStatus().Diag = nullptr;
+  return true;
+}
+inline bool EndSpeculation(InterpState &S, CodePtr OpPC) {
+  assert(S.SpeculationDepth != 0);
+  --S.SpeculationDepth;
+  if (S.SpeculationDepth == 0) {
+    S.getEvalStatus().Diag = S.PrevDiags;
+    S.PrevDiags = nullptr;
+  }
+  return true;
+}
+
 /// Do nothing and just abort execution.
 inline bool Error(InterpState &S, CodePtr OpPC) { return false; }
+
 inline bool SideEffect(InterpState &S, CodePtr OpPC) {
   return S.noteSideEffect();
 }
diff --git a/clang/lib/AST/ByteCode/InterpBuiltin.cpp b/clang/lib/AST/ByteCode/InterpBuiltin.cpp
@@ -1483,80 +1483,6 @@ static bool interp__builtin_ptrauth_string_discriminator(
   return true;
 }
 
-// FIXME: This implementation is not complete.
-// The Compiler instance we create cannot access the current stack frame, local
-// variables, function parameters, etc. We also need protection from
-// side-effects, fatal errors, etc.
-static bool interp__builtin_constant_p(InterpState &S, CodePtr OpPC,
-                                       const InterpFrame *Frame,
-                                       const Function *Func,
-                                       const CallExpr *Call) {
-  const Expr *Arg = Call->getArg(0);
-  QualType ArgType = Arg->getType();
-
-  auto returnInt = [&S, Call](bool Value) -> bool {
-    pushInteger(S, Value, Call->getType());
-    return true;
-  };
-
-  // __builtin_constant_p always has one operand. The rules which gcc follows
-  // are not precisely documented, but are as follows:
-  //
-  //  - If the operand is of integral, floating, complex or enumeration type,
-  //    and can be folded to a known value of that type, it returns 1.
-  //  - If the operand can be folded to a pointer to the first character
-  //    of a string literal (or such a pointer cast to an integral type)
-  //    or to a null pointer or an integer cast to a pointer, it returns 1.
-  //
-  // Otherwise, it returns 0.
-  //
-  // FIXME: GCC also intends to return 1 for literals of aggregate types, but
-  // its support for this did not work prior to GCC 9 and is not yet well
-  // understood.
-  if (ArgType->isIntegralOrEnumerationType() || ArgType->isFloatingType() ||
-      ArgType->isAnyComplexType() || ArgType->isPointerType() ||
-      ArgType->isNullPtrType()) {
-    auto PrevDiags = S.getEvalStatus().Diag;
-    S.getEvalStatus().Diag = nullptr;
-    InterpStack Stk;
-    Compiler<EvalEmitter> C(S.Ctx, S.P, S, Stk);
-    auto Res = C.interpretExpr(Arg, /*ConvertResultToRValue=*/Arg->isGLValue());
-    S.getEvalStatus().Diag = PrevDiags;
-    if (Res.isInvalid()) {
-      C.cleanup();
-      Stk.clear();
-      return returnInt(false);
-    }
-
-    if (!Res.empty()) {
-      const APValue &LV = Res.toAPValue();
-      if (LV.isLValue()) {
-        APValue::LValueBase Base = LV.getLValueBase();
-        if (Base.isNull()) {
-          // A null base is acceptable.
-          return returnInt(true);
-        } else if (const auto *E = Base.dyn_cast<const Expr *>()) {
-          if (!isa<StringLiteral>(E))
-            return returnInt(false);
-          return returnInt(LV.getLValueOffset().isZero());
-        } else if (Base.is<TypeInfoLValue>()) {
-          // Surprisingly, GCC considers __builtin_constant_p(&typeid(int)) to
-          // evaluate to true.
-          return returnInt(true);
-        } else {
-          // Any other base is not constant enough for GCC.
-          return returnInt(false);
-        }
-      }
-    }
-
-    // Otherwise, any constant value is good enough.
-    return returnInt(true);
-  }
-
-  return returnInt(false);
-}
-
 static bool interp__builtin_operator_new(InterpState &S, CodePtr OpPC,
                                          const InterpFrame *Frame,
                                          const Function *Func,
@@ -2468,11 +2394,6 @@ bool InterpretBuiltin(InterpState &S, CodePtr OpPC, const Function *F,
       return false;
     break;
 
-  case Builtin::BI__builtin_constant_p:
-    if (!interp__builtin_constant_p(S, OpPC, Frame, F, Call))
-      return false;
-    break;
-
   case Builtin::BI__noop:
     pushInteger(S, 0, Call->getType());
     break;
diff --git a/clang/lib/AST/ByteCode/InterpState.h b/clang/lib/AST/ByteCode/InterpState.h
@@ -144,6 +144,9 @@ class InterpState final : public State, public SourceMapper {
   SourceLocation EvalLocation;
   /// Declaration we're initializing/evaluting, if any.
   const VarDecl *EvaluatingDecl = nullptr;
+  /// Things needed to do speculative execution.
+  SmallVectorImpl<PartialDiagnosticAt> *PrevDiags = nullptr;
+  unsigned SpeculationDepth = 0;
 
   llvm::SmallVector<
       std::pair<const Expr *, const LifetimeExtendedTemporaryDecl *>>
diff --git a/clang/lib/AST/ByteCode/Opcodes.td b/clang/lib/AST/ByteCode/Opcodes.td
diff --git a/clang/test/AST/ByteCode/builtin-constant-p.cpp b/clang/test/AST/ByteCode/builtin-constant-p.cpp
diff --git a/clang/test/CodeGen/builtin-constant-p.c b/clang/test/CodeGen/builtin-constant-p.c
diff --git a/clang/test/CodeGenCXX/builtin-constant-p.cpp b/clang/test/CodeGenCXX/builtin-constant-p.cpp
