diff --git a/llvm/include/llvm/Transforms/Utils/Cloning.h b/llvm/include/llvm/Transforms/Utils/Cloning.h
--- a/llvm/include/llvm/Transforms/Utils/Cloning.h
+++ b/llvm/include/llvm/Transforms/Utils/Cloning.h
@@ -197,9 +197,10 @@
       function_ref<AssumptionCache &(Function &)> GetAssumptionCache = nullptr,
       ProfileSummaryInfo *PSI = nullptr,
       BlockFrequencyInfo *CallerBFI = nullptr,
-      BlockFrequencyInfo *CalleeBFI = nullptr)
+      BlockFrequencyInfo *CalleeBFI = nullptr, bool UpdateProfile = true)
       : CG(cg), GetAssumptionCache(GetAssumptionCache), PSI(PSI),
-        CallerBFI(CallerBFI), CalleeBFI(CalleeBFI) {}
+        CallerBFI(CallerBFI), CalleeBFI(CalleeBFI),
+        UpdateProfile(UpdateProfile) {}
 
   /// If non-null, InlineFunction will update the callgraph to reflect the
   /// changes it makes.
@@ -223,6 +224,10 @@
   /// `InlinedCalls` above is used.
   SmallVector<CallBase *, 8> InlinedCallSites;
 
+  /// Update profile for callee as well as cloned version. We need to do this
+  /// for regular inlining, but not for inlining from sample profile loader.
+  bool UpdateProfile;
+
   void reset() {
     StaticAllocas.clear();
     InlinedCalls.clear();
diff --git a/llvm/lib/Transforms/IPO/SampleProfile.cpp b/llvm/lib/Transforms/IPO/SampleProfile.cpp
--- a/llvm/lib/Transforms/IPO/SampleProfile.cpp
+++ b/llvm/lib/Transforms/IPO/SampleProfile.cpp
@@ -1093,6 +1093,7 @@
     return false;
 
   InlineFunctionInfo IFI(nullptr, GetAC);
+  IFI.UpdateProfile = false;
   if (InlineFunction(CB, IFI).isSuccess()) {
     // The call to InlineFunction erases I, so we can't pass it here.
     emitInlinedInto(*ORE, DLoc, BB, *CalledFunction, *BB->getParent(), Cost,
diff --git a/llvm/lib/Transforms/Utils/InlineFunction.cpp b/llvm/lib/Transforms/Utils/InlineFunction.cpp
--- a/llvm/lib/Transforms/Utils/InlineFunction.cpp
+++ b/llvm/lib/Transforms/Utils/InlineFunction.cpp
@@ -1954,13 +1954,19 @@
     if (objcarc::hasAttachedCallOpBundle(&CB))
       inlineRetainOrClaimRVCalls(CB, Returns);
 
-    if (IFI.CallerBFI != nullptr && IFI.CalleeBFI != nullptr)
-      // Update the BFI of blocks cloned into the caller.
-      updateCallerBFI(OrigBB, VMap, IFI.CallerBFI, IFI.CalleeBFI,
-                      CalledFunc->front());
-
-    updateCallProfile(CalledFunc, VMap, CalledFunc->getEntryCount(), CB,
-                      IFI.PSI, IFI.CallerBFI);
+    // Updated caller/callee profiles only when requested. For sample loader
+    // inlining, the context-sensitive inlinee profile doesn't need to be
+    // subtracted from callee profile, and the inlined clone also doesn't need
+    // to be scaled based on call site count.
+    if (IFI.UpdateProfile) {
+      if (IFI.CallerBFI != nullptr && IFI.CalleeBFI != nullptr)
+        // Update the BFI of blocks cloned into the caller.
+        updateCallerBFI(OrigBB, VMap, IFI.CallerBFI, IFI.CalleeBFI,
+                        CalledFunc->front());
+
+      updateCallProfile(CalledFunc, VMap, CalledFunc->getEntryCount(), CB,
+                        IFI.PSI, IFI.CallerBFI);
+    }
 
     // Inject byval arguments initialization.
     for (std::pair<Value*, Value*> &Init : ByValInit)