4 files changed, 38 insertions, 24 deletions

diff --git a/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp b/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
index 284b984f0a..495418d999 100644
--- a/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
+++ b/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
@@ -4197,8 +4197,9 @@ SelectionDAGBuilder::visitIntrinsicCall(CallInst &I, unsigned Intrinsic) {
 ///
 /// This function only tests target-independent requirements.
 static bool
-isInTailCallPosition(const Instruction *I, Attributes CalleeRetAttr,
+isInTailCallPosition(CallSite CS, Attributes CalleeRetAttr,
                      const TargetLowering &TLI) {
+  const Instruction *I = CS.getInstruction();
   const BasicBlock *ExitBB = I->getParent();
   const TerminatorInst *Term = ExitBB->getTerminator();
   const ReturnInst *Ret = dyn_cast<ReturnInst>(Term);
@@ -4207,6 +4208,12 @@ isInTailCallPosition(const Instruction *I, Attributes CalleeRetAttr,
   // The block must end in a return statement or an unreachable.
   if (!Ret && !isa<UnreachableInst>(Term)) return false;
 
+  // Unless we are explicitly forcing tailcall optimization do not tailcall if
+  // the called function is bitcast'ed. The analysis may not be entirely
+  // accurate.
+  if (!PerformTailCallOpt && isa<BitCastInst>(CS.getCalledValue()))
+    return false;
+
   // If I will have a chain, make sure no other instruction that will have a
   // chain interposes between I and the return.
   if (I->mayHaveSideEffects() || I->mayReadFromMemory() ||
@@ -4348,9 +4355,7 @@ void SelectionDAGBuilder::LowerCallTo(CallSite CS, SDValue Callee,
   // Check if target-independent constraints permit a tail call here.
   // Target-dependent constraints are checked within TLI.LowerCallTo.
   if (isTailCall &&
-      !isInTailCallPosition(CS.getInstruction(),
-                            CS.getAttributes().getRetAttributes(),
-                            TLI))
+      !isInTailCallPosition(CS, CS.getAttributes().getRetAttributes(), TLI))
     isTailCall = false;
 
   std::pair<SDValue,SDValue> Result =
diff --git a/lib/Target/X86/X86ISelLowering.cpp b/lib/Target/X86/X86ISelLowering.cpp
index 6f710ecbe1..9d6b5a39b2 100644
--- a/lib/Target/X86/X86ISelLowering.cpp
+++ b/lib/Target/X86/X86ISelLowering.cpp
@@ -2269,7 +2269,6 @@ X86TargetLowering::IsEligibleForTailCallOptimization(SDValue Callee,
     return false;
   }
 
-
   // Look for obvious safe cases to perform tail call optimization that does not
   // requite ABI changes. This is what gcc calls sibcall.
 
@@ -2324,22 +2323,7 @@ X86TargetLowering::IsEligibleForTailCallOptimization(SDValue Callee,
     }
   }
 
-  // If the caller does not return a value, then this is obviously safe.
-  // This is one case where it's safe to perform this optimization even
-  // if the return types do not match.
-  const Type *CallerRetTy = CallerF->getReturnType();
-  if (CallerRetTy->isVoidTy())
-    return true;
-
-  // If the return types match, then it's safe.
-  // Don't tail call optimize recursive call.
-  GlobalAddressSDNode *G = dyn_cast<GlobalAddressSDNode>(Callee);
-  if (!G) return false;  // FIXME: common external symbols?
-  if (const Function *CalleeF = dyn_cast<Function>(G->getGlobal())) {
-    const Type *CalleeRetTy = CalleeF->getReturnType();
-    return CallerRetTy == CalleeRetTy;
-  }
-  return false;
+  return true;
 }
 
 FastISel *
diff --git a/test/CodeGen/X86/tailcall2.ll b/test/CodeGen/X86/tailcall2.ll
index e41e3da4f8..81419dc387 100644
--- a/test/CodeGen/X86/tailcall2.ll
+++ b/test/CodeGen/X86/tailcall2.ll
@@ -102,3 +102,28 @@ entry:
 }
 
 declare i32 @bar2(i32, i32, i32)
+
+define signext i16 @t8() nounwind ssp {
+entry:
+; 32: t8:
+; 32: jmp {{_?}}bar3
+
+; 64: t8:
+; 64: jmp {{_?}}bar3
+  %0 = tail call signext i16 @bar3() nounwind      ; <i16> [#uses=1]
+  ret i16 %0
+}
+
+declare signext i16 @bar3()
+
+define signext i16 @t9(i32 (i32)* nocapture %x) nounwind ssp {
+entry:
+; 32: t9:
+; 32: call *
+
+; 64: t9:
+; 64: callq *
+  %0 = bitcast i32 (i32)* %x to i16 (i32)*
+  %1 = tail call signext i16 %0(i32 0) nounwind
+  ret i16 %1
+}
diff --git a/test/CodeGen/X86/tailcallfp2.ll b/test/CodeGen/X86/tailcallfp2.ll
index be4f96cfb5..3841f51897 100644
--- a/test/CodeGen/X86/tailcallfp2.ll
+++ b/test/CodeGen/X86/tailcallfp2.ll
@@ -2,7 +2,7 @@
 
 declare i32 @putchar(i32)
 
-define fastcc i32 @checktail(i32 %x, i32* %f, i32 %g) {
+define fastcc i32 @checktail(i32 %x, i32* %f, i32 %g) nounwind {
         %tmp1 = icmp sgt i32 %x, 0
         br i1 %tmp1, label %if-then, label %if-else
 
@@ -18,8 +18,8 @@ if-else:
 }
 
 
-define i32 @main() { 
+define i32 @main() nounwind { 
  %f   = bitcast i32 (i32, i32*, i32)* @checktail to i32*
  %res = tail call fastcc i32 @checktail( i32 10, i32* %f,i32 10)
  ret i32 %res
-}
\ No newline at end of file
+}