Index: lib/Transforms/IPO/PassManagerBuilder.cpp
===================================================================
--- lib/Transforms/IPO/PassManagerBuilder.cpp
+++ lib/Transforms/IPO/PassManagerBuilder.cpp
@@ -125,6 +125,15 @@
     "enable-loop-versioning-licm", cl::init(false), cl::Hidden,
     cl::desc("Enable the experimental Loop Versioning LICM pass"));
 
+static cl::opt<bool>
+    DisablePreInliner("disable-preinline", cl::init(false), cl::Hidden,
+                      cl::desc("Disable pre-instrumentation inliner"));
+
+static cl::opt<int> PreInlineThreshold(
+    "preinline-threshold", cl::Hidden, cl::init(75), cl::ZeroOrMore,
+    cl::desc("Control the amount of inlining in pre-instrumentation inliner "
+             "(default = 75)"));
+
 PassManagerBuilder::PassManagerBuilder() {
     OptLevel = 2;
     SizeLevel = 0;
@@ -228,6 +237,19 @@
 
 // Do PGO instrumentation generation or use pass as the option specified.
 void PassManagerBuilder::addPGOInstrPasses(legacy::PassManagerBase &MPM) {
+  if (PGOInstrGen.empty() && PGOInstrUse.empty())
+    return;
+  // Perform the preinline and cleanup passes for O1 and above.
+  // And avoid doing them if optimizing for size.
+  if (OptLevel > 0 && SizeLevel == 0 && !DisablePreInliner) {
+    // Create preinline pass.
+    MPM.add(createFunctionInliningPass(PreInlineThreshold));
+    MPM.add(createSROAPass());
+    MPM.add(createEarlyCSEPass());             // Catch trivial redundancies
+    MPM.add(createCFGSimplificationPass());    // Merge & remove BBs
+    MPM.add(createInstructionCombiningPass()); // Combine silly seq's
+    addExtensionsToPM(EP_Peephole, MPM);
+  }
   if (!PGOInstrGen.empty()) {
     MPM.add(createPGOInstrumentationGenLegacyPass());
     // Add the profile lowering pass.
Index: test/Transforms/PGOProfile/preinline.ll
===================================================================
--- /dev/null
+++ test/Transforms/PGOProfile/preinline.ll
@@ -0,0 +1,21 @@
+; RUN: opt < %s -O2 -profile-generate=default.profraw -S | FileCheck %s --check-prefix=GEN
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+define i32 @foo(i32 %i) {
+entry:
+; GEN: %pgocount = load i64, i64* getelementptr inbounds ([1 x i64], [1 x i64]* @__profc_foo
+; GEN-NOT: %pgocount.i = load i64, i64* getelementptr inbounds ([1 x i64], [1 x i64]* @__profc__stdin__bar
+  %call = call i32 @bar()
+  %add = add nsw i32 %i, %call
+  ret i32 %add
+}
+
+define internal i32 @bar() {
+; GEN-NOT: define internal i32 @bar
+entry:
+  %call = call i32 (...) @bar1()
+  ret i32 %call
+}
+
+declare i32 @bar1(...)