Index: lib/Analysis/InlineCost.cpp
===================================================================
--- lib/Analysis/InlineCost.cpp
+++ lib/Analysis/InlineCost.cpp
@@ -54,6 +54,11 @@
                           cl::init(45),
                           cl::desc("Threshold for inlining cold callsites"));
 
+cl::opt<bool> DisableCygprofileInlining(
+    "disable-cygprofile-inlining",
+    cl::desc("Disable inlining of calls to __cyg_profile functions"),
+    cl::init(false));
+
 // We introduce this threshold to help performance of instrumentation based
 // PGO before we actually hook up inliner with analysis passes such as BPI and
 // BFI.
@@ -1072,10 +1077,18 @@
     ExposesReturnsTwice = true;
     return false;
   }
+
   if (CS.isCall() && cast<CallInst>(CS.getInstruction())->cannotDuplicate())
     ContainsNoDuplicateCall = true;
 
   if (Function *F = CS.getCalledFunction()) {
+    // Ignore call instructions generated by -fprofile-functions. They will not
+    // be cloned, and should not affect the inlining decision.
+    if (DisableCygprofileInlining &&
+        (F->getName() == "__cyg_profile_func_enter" ||
+         F->getName() == "__cyg_profile_func_exit"))
+      return false;
+
     // When we have a concrete function, first try to simplify it directly.
     if (simplifyCallSite(F, CS))
       return true;
Index: lib/Transforms/Utils/CloneFunction.cpp
===================================================================
--- lib/Transforms/Utils/CloneFunction.cpp
+++ lib/Transforms/Utils/CloneFunction.cpp
@@ -36,6 +36,8 @@
 #include <map>
 using namespace llvm;
 
+extern cl::opt<bool> DisableCygprofileInlining;
+
 /// See comments in Cloning.h.
 BasicBlock *llvm::CloneBasicBlock(const BasicBlock *BB, ValueToValueMapTy &VMap,
                                   const Twine &NameSuffix, Function *F,
@@ -298,7 +300,8 @@
 
   // Have we already cloned this block?
   if (BBEntry) return;
-  
+
+
   // Nope, clone it now.
   BasicBlock *NewBB;
   BBEntry = NewBB = BasicBlock::Create(BB->getContext());
@@ -325,6 +328,16 @@
   // loop doesn't include the terminator.
   for (BasicBlock::const_iterator II = StartingInst, IE = --BB->end();
        II != IE; ++II) {
+    // Drop call instructions generated by -fprofile-functions.
+    if (DisableCygprofileInlining) {
+      if (const CallInst *CI = dyn_cast<CallInst>(II)) {
+        if (const Function *Callee = CI->getCalledFunction()) {
+          if (Callee->getName() == "__cyg_profile_func_enter" ||
+              Callee->getName() == "__cyg_profile_func_exit")
+            continue;
+        }
+      }
+    }
 
     Instruction *NewInst = II->clone();
 
Index: test/Transforms/Inline/cygprofile-instrumentation.ll
===================================================================
--- /dev/null
+++ test/Transforms/Inline/cygprofile-instrumentation.ll
@@ -0,0 +1,39 @@
+; RUN: opt < %s -inline -S | FileCheck %s --check-prefix=CHECK --check-prefix=INLINE
+; RUN: opt < %s -inline -inline-threshold=1 -disable-cygprofile-inlining -S | FileCheck %s --check-prefix=CHECK --check-prefix=NOINLINE
+
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+
+declare void @__cyg_profile_func_enter(i8*, i8*)
+declare void @__cyg_profile_func_exit(i8*, i8*)
+declare i8* @llvm.returnaddress(i32)
+
+define internal void @g() {
+entry:
+  %callsite = call i8* @llvm.returnaddress(i32 0)
+  call void @__cyg_profile_func_enter(i8* bitcast (void ()* @g to i8*), i8* %callsite)
+  %callsite1 = call i8* @llvm.returnaddress(i32 0)
+  call void @__cyg_profile_func_exit(i8* bitcast (void ()* @g to i8*), i8* %callsite1)
+  ret void
+}
+
+define void @f() {
+; CHECK-LABEL: @f
+; The call to @g should be inlined, but whether or not @g's cygprofile calls
+; should be inlined depends on the use of -disable-cygprofile-inlining.
+
+; CHECK: call void @__cyg_profile_func_enter
+; CHECK-NOT: call void @g()
+; INLINE: call void @__cyg_profile_func_enter
+; NOINLINE-NOT: call void @__cyg_profile_func_enter
+; CHECK: call void @__cyg_profile_func_exit
+; INLINE: call void @__cyg_profile_func_exit
+; NOINLINE-NOT: call void @__cyg_profile_func_exit
+
+entry:
+  %callsite = call i8* @llvm.returnaddress(i32 0)
+  call void @__cyg_profile_func_enter(i8* bitcast (void ()* @f to i8*), i8* %callsite)
+  call void @g()
+  %callsite1 = call i8* @llvm.returnaddress(i32 0)
+  call void @__cyg_profile_func_exit(i8* bitcast (void ()* @f to i8*), i8* %callsite1)
+  ret void
+}