Index: lib/CodeGen/CodeGenFunction.cpp
===================================================================
--- lib/CodeGen/CodeGenFunction.cpp
+++ lib/CodeGen/CodeGenFunction.cpp
@@ -428,14 +428,6 @@
   EmitNounwindRuntimeCall(F, args);
 }
 
-void CodeGenFunction::EmitMCountInstrumentation() {
-  llvm::FunctionType *FTy = llvm::FunctionType::get(VoidTy, false);
-
-  llvm::Constant *MCountFn =
-    CGM.CreateRuntimeFunction(FTy, getTarget().getMCountName());
-  EmitNounwindRuntimeCall(MCountFn);
-}
-
 // OpenCL v1.2 s5.6.4.6 allows the compiler to store kernel argument
 // information in the program executable. The argument information stored
 // includes the argument name, its type, the address and access qualifiers used.
@@ -794,8 +786,12 @@
   if (ShouldInstrumentFunction())
     EmitFunctionInstrumentation("__cyg_profile_func_enter");
 
+  // Since emitting the mcount call here impacts optimizations such as function
+  // inlining, we just add an attribute to insert a mcount call in backend.
+  // The attribute "counting-function" is set to mcount function name which is
+  // architecture dependent.
   if (CGM.getCodeGenOpts().InstrumentForProfiling)
-    EmitMCountInstrumentation();
+    Fn->addFnAttr("counting-function", getTarget().getMCountName());
 
   if (RetTy->isVoidType()) {
     // Void type; nothing to return.
Index: test/CodeGen/mcount.c
===================================================================
--- test/CodeGen/mcount.c
+++ test/CodeGen/mcount.c
@@ -1,4 +1,5 @@
 // RUN: %clang_cc1 -pg -triple i386-unknown-unknown -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -pg -triple i386-unknown-unknown -emit-llvm -O2 -o - %s | FileCheck %s
 // RUN: %clang_cc1 -pg -triple powerpc-unknown-gnu-linux -emit-llvm -o - %s | FileCheck -check-prefix=CHECK-PREFIXED %s
 // RUN: %clang_cc1 -pg -triple powerpc64-unknown-gnu-linux -emit-llvm -o - %s | FileCheck -check-prefix=CHECK-PREFIXED %s
 // RUN: %clang_cc1 -pg -triple powerpc64le-unknown-gnu-linux -emit-llvm -o - %s | FileCheck -check-prefix=CHECK-PREFIXED %s
@@ -12,7 +13,20 @@
 // RUN: %clang_cc1 -pg -triple powerpc64le-netbsd -emit-llvm -o - %s | FileCheck -check-prefix=CHECK-PREFIXED %s
 // RUN: %clang_cc1 -pg -triple sparc-netbsd -emit-llvm -o - %s | FileCheck -check-prefix=CHECK-PREFIXED %s
 // RUN: %clang_cc1 -pg -triple sparc64-netbsd -emit-llvm -o - %s | FileCheck -check-prefix=CHECK-PREFIXED %s
-void foo(void) {
-// CHECK: call void @mcount()
-// CHECK-PREFIXED: call void @_mcount()
+// RUN: %clang_cc1 -emit-llvm -o - %s | FileCheck %s -check-prefix=NO-MCOUNT
+
+int bar(void) {
+  return 0;
 }
+
+int foo(void) {
+  return bar();
+}
+
+int main(void) {
+  return foo();
+}
+
+// CHECK: attributes #{{[0-9]+}} = { {{.*}}"counting-function"="mcount"{{.*}} }
+// CHECK-PREFIXED: attributes #{{[0-9]+}} = { {{.*}}"counting-function"="_mcount"{{.*}} }
+// NO-MCOUNT-NOT: attributes #{{[0-9]}} = { {{.*}}"counting-function"={{.*}} }