diff --git a/llvm/lib/ProfileData/SampleProf.cpp b/llvm/lib/ProfileData/SampleProf.cpp
--- a/llvm/lib/ProfileData/SampleProf.cpp
+++ b/llvm/lib/ProfileData/SampleProf.cpp
@@ -371,9 +371,7 @@
 
 void SampleContextTrimmer::canonicalizeContextProfiles() {
   StringSet<> ProfilesToBeRemoved;
-  // Note that StringMap order is guaranteed to be top-down order,
-  // this makes sure we make room for promoted/merged context in the
-  // map, before we move profiles in the map.
+  StringMap<FunctionSamples> ProfilesToBeAdded;
   for (auto &I : ProfileMap) {
     FunctionSamples &FProfile = I.second;
     StringRef ContextStr = FProfile.getNameWithContext();
@@ -383,18 +381,19 @@
     // Use the context string from FunctionSamples to update the keys of
     // ProfileMap. They can get out of sync after context profile promotion
     // through pre-inliner.
-    auto Ret = ProfileMap.try_emplace(ContextStr, FProfile);
-    assert(Ret.second && "Conext conflict during canonicalization");
-    FProfile = Ret.first->second;
-
-    // Track the context profile to remove
-    ProfilesToBeRemoved.erase(ContextStr);
+    auto Ret = ProfilesToBeAdded.try_emplace(ContextStr, FProfile);
+    (void)Ret;
+    assert(Ret.second && "Context conflict during canonicalization");
     ProfilesToBeRemoved.insert(I.first());
   }
 
   for (auto &I : ProfilesToBeRemoved) {
     ProfileMap.erase(I.first());
   }
+
+  for (auto &I : ProfilesToBeAdded) {
+    ProfileMap.try_emplace(I.first(), I.second);
+  }
 }
 
 std::error_code ProfileSymbolList::write(raw_ostream &OS) {
diff --git a/llvm/tools/llvm-profgen/CSPreInliner.cpp b/llvm/tools/llvm-profgen/CSPreInliner.cpp
--- a/llvm/tools/llvm-profgen/CSPreInliner.cpp
+++ b/llvm/tools/llvm-profgen/CSPreInliner.cpp
@@ -16,11 +16,6 @@
 using namespace llvm;
 using namespace sampleprof;
 
-static cl::opt<bool> EnableCSPreInliner(
-    "csspgo-preinliner", cl::Hidden, cl::init(false),
-    cl::desc("Run a global pre-inliner to merge context profile based on "
-             "estimated global top-down inline decisions"));
-
 // The switches specify inline thresholds used in SampleProfileLoader inlining.
 // TODO: the actual threshold to be tuned here because the size here is based
 // on machine code not LLVM IR.
@@ -179,9 +174,6 @@
 }
 
 void CSPreInliner::run() {
-  if (!EnableCSPreInliner)
-    return;
-
 #ifndef NDEBUG
   auto printProfileNames = [](StringMap<FunctionSamples> &Profiles,
                               bool IsInput) {
diff --git a/llvm/tools/llvm-profgen/ProfileGenerator.cpp b/llvm/tools/llvm-profgen/ProfileGenerator.cpp
--- a/llvm/tools/llvm-profgen/ProfileGenerator.cpp
+++ b/llvm/tools/llvm-profgen/ProfileGenerator.cpp
@@ -48,6 +48,11 @@
     cl::desc("Keep the last K frames while merging cold profile. 1 means the "
              "context-less base profile"));
 
+static cl::opt<bool> EnableCSPreInliner(
+    "csspgo-preinliner", cl::Hidden, cl::init(false),
+    cl::desc("Run a global pre-inliner to merge context profile based on "
+             "estimated global top-down inline decisions"));
+
 extern cl::opt<int> ProfileSummaryCutoffCold;
 
 using namespace llvm;
@@ -401,7 +406,8 @@
 
   // Run global pre-inliner to adjust/merge context profile based on estimated
   // inline decisions.
-  CSPreInliner(ProfileMap, HotCountThreshold, ColdCountThreshold).run();
+  if (EnableCSPreInliner)
+    CSPreInliner(ProfileMap, HotCountThreshold, ColdCountThreshold).run();
 
   // Trim and merge cold context profile using cold threshold above;
   SampleContextTrimmer(ProfileMap)