diff --git a/lib/CodeGen/SelectionDAG/TargetLowering.cpp b/lib/CodeGen/SelectionDAG/TargetLowering.cpp
index ab4cd51..134a859 100644
--- a/lib/CodeGen/SelectionDAG/TargetLowering.cpp
+++ b/lib/CodeGen/SelectionDAG/TargetLowering.cpp
@@ -2584,8 +2584,12 @@
   // Check that operand of the RET node sources from the CALL node. The RET node
   // has at least two operands. Operand 0 holds the chain. Operand 1 holds the
   // value.
+  // Also we need to check that there is no code in between the call and the
+  // return. Hence we also check that the incomming chain to the return sources
+  // from the outgoing chain of the call.
   if (NumOps > 1 &&
-      IgnoreHarmlessInstructions(Ret.getOperand(1)) == SDValue(TheCall,0))
+      IgnoreHarmlessInstructions(Ret.getOperand(1)) == SDValue(TheCall,0) &&
+      Ret.getOperand(0) == SDValue(TheCall, TheCall->getNumValues()-1))
     return true;
   // void return: The RET node  has the chain result value of the CALL node as
   // input.
diff --git a/test/CodeGen/X86/2009-06-15-not-a-tail-call.ll b/test/CodeGen/X86/2009-06-15-not-a-tail-call.ll
new file mode 100644
index 0000000..095e6a1
--- /dev/null
+++ b/test/CodeGen/X86/2009-06-15-not-a-tail-call.ll
@@ -0,0 +1,14 @@
+; RUN: llvm-as < %s | llc -march=x86 -tailcallopt | not grep TAILCALL 
+
+; Bug 4396. This tail call can NOT be optimized.
+
+declare fastcc i8* @_D3gcx2GC12mallocNoSyncMFmkZPv() nounwind
+
+define fastcc i8* @_D3gcx2GC12callocNoSyncMFmkZPv() nounwind {
+entry:
+	%tmp6 = tail call fastcc i8* @_D3gcx2GC12mallocNoSyncMFmkZPv()		; <i8*> [#uses=2]
+	%tmp9 = tail call i8* @memset(i8* %tmp6, i32 0, i64 2)		; <i8*> [#uses=0]
+	ret i8* %tmp6
+}
+
+declare i8* @memset(i8*, i32, i64)