diff --git a/llvm/include/llvm/ProfileData/SampleProf.h b/llvm/include/llvm/ProfileData/SampleProf.h
--- a/llvm/include/llvm/ProfileData/SampleProf.h
+++ b/llvm/include/llvm/ProfileData/SampleProf.h
@@ -206,7 +206,8 @@
 enum class SecFuncMetadataFlags : uint32_t {
   SecFlagInvalid = 0,
   SecFlagIsProbeBased = (1 << 0),
-  SecFlagHasAttribute = (1 << 1)
+  SecFlagHasAttribute = (1 << 1),
+  SecFlagIsPreInlined = (2 << 1),
 };
 
 enum class SecFuncOffsetFlags : uint32_t {
@@ -591,11 +592,11 @@
                         : hash_value(getName());
   }
 
-  /// Set the name of the function.
+  /// Set the name of the function and clear the current context.
   void setName(StringRef FunctionName) {
-    assert(FullContext.empty() &&
-           "setName should only be called for non-CS profile");
     Name = FunctionName;
+    FullContext = SampleContextFrames();
+    State = UnknownContext;
   }
 
   void setContext(SampleContextFrames Context,
@@ -745,6 +746,16 @@
     }
   }
 
+  // Set current context and all callee contexts to be synthetic.
+  void SetContextSynthetic() {
+    Context.setState(SyntheticContext);
+    for (auto &I : CallsiteSamples) {
+      for (auto &CS : I.second) {
+        CS.second.SetContextSynthetic();
+      }
+    }
+  }
+
   /// Return the number of samples collected at the given location.
   /// Each location is specified by \p LineOffset and \p Discriminator.
   /// If the location is not found in profile, return error.
@@ -1010,6 +1021,11 @@
   /// the context tracker.
   static LineLocation getCallSiteIdentifier(const DILocation *DIL);
 
+  /// Returns a unique hash code for a combination of a callsite location and
+  /// the callee function name.
+  static uint64_t getCallSiteHash(StringRef CalleeName,
+                                  const LineLocation &Callsite);
+
   /// Get the FunctionSamples of the inline instance where DIL originates
   /// from.
   ///
@@ -1029,6 +1045,8 @@
 
   static bool ProfileIsCS;
 
+  static bool ProfileIsPreinlined;
+
   SampleContext &getContext() const { return Context; }
 
   void setContext(const SampleContext &FContext) { Context = FContext; }
@@ -1161,6 +1179,38 @@
   SampleProfileMap &ProfileMap;
 };
 
+class CSProfileConverter {
+public:
+  CSProfileConverter(SampleProfileMap &Profiles);
+  void convertProfiles();
+  struct FrameNode {
+    FrameNode(StringRef FName = StringRef(),
+              FunctionSamples *FSamples = nullptr,
+              LineLocation CallLoc = {0, 0})
+        : FuncName(FName), FuncSamples(FSamples), CallSiteLoc(CallLoc){};
+
+    // Map line+discriminator location to child frame
+    std::map<uint64_t, FrameNode> AllChildFrames;
+    // Function name for current frame
+    StringRef FuncName;
+    // Function Samples for current frame
+    FunctionSamples *FuncSamples;
+    // Callsite location in parent context
+    LineLocation CallSiteLoc;
+
+    FrameNode *getOrCreateChildFrame(const LineLocation &CallSite,
+                                     StringRef CalleeName);
+  };
+
+private:
+  // Nest all children profiles into the profile of Node.
+  void convertProfiles(FrameNode &Node);
+  FrameNode *getOrCreateContextPath(const SampleContext &Context);
+
+  SampleProfileMap &ProfileMap;
+  FrameNode RootFrame;
+};
+
 /// ProfileSymbolList records the list of function symbols shown up
 /// in the binary used to generate the profile. It is useful to
 /// to discriminate a function being so cold as not to shown up
diff --git a/llvm/include/llvm/ProfileData/SampleProfReader.h b/llvm/include/llvm/ProfileData/SampleProfReader.h
--- a/llvm/include/llvm/ProfileData/SampleProfReader.h
+++ b/llvm/include/llvm/ProfileData/SampleProfReader.h
@@ -476,6 +476,8 @@
   /// Whether input profile is fully context-sensitive
   bool profileIsCS() const { return ProfileIsCS; }
 
+  bool profileIsPreinlined() const { return ProfileIsPreinlined; }
+
   virtual std::unique_ptr<ProfileSymbolList> getProfileSymbolList() {
     return nullptr;
   };
@@ -536,6 +538,10 @@
   /// Whether function profiles are context-sensitive.
   bool ProfileIsCS = false;
 
+  /// Whether function profiles are generated by the CS preinliner with full
+  /// inline decisions made.
+  bool ProfileIsPreinlined = false;
+
   /// Number of context-sensitive profiles.
   uint32_t CSProfileCount = 0;
 
@@ -698,6 +704,8 @@
   std::error_code readSecHdrTable();
 
   std::error_code readFuncMetadata(bool ProfileHasAttribute);
+  std::error_code readFuncMetadata(bool ProfileHasAttribute,
+                                   FunctionSamples *FProfile, bool Inlined);
   std::error_code readFuncOffsetTable();
   std::error_code readFuncProfiles();
   std::error_code readMD5NameTable();
diff --git a/llvm/include/llvm/ProfileData/SampleProfWriter.h b/llvm/include/llvm/ProfileData/SampleProfWriter.h
--- a/llvm/include/llvm/ProfileData/SampleProfWriter.h
+++ b/llvm/include/llvm/ProfileData/SampleProfWriter.h
@@ -269,6 +269,7 @@
   std::error_code writeCSNameTableSection();
 
   std::error_code writeFuncMetadata(const SampleProfileMap &Profiles);
+  std::error_code writeFuncMetadata(const FunctionSamples &Profile);
 
   // Functions to write various kinds of sections.
   std::error_code writeNameTableSection(const SampleProfileMap &ProfileMap);
diff --git a/llvm/include/llvm/Transforms/IPO/SampleContextTracker.h b/llvm/include/llvm/Transforms/IPO/SampleContextTracker.h
--- a/llvm/include/llvm/Transforms/IPO/SampleContextTracker.h
+++ b/llvm/include/llvm/Transforms/IPO/SampleContextTracker.h
@@ -66,8 +66,6 @@
   void dumpTree();
 
 private:
-  static uint64_t nodeHash(StringRef ChildName, const LineLocation &Callsite);
-
   // Map line+discriminator location to child context
   std::map<uint64_t, ContextTrieNode> AllChildContext;
 
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
@@ -35,11 +35,18 @@
     cl::desc("Cutoff value about how many symbols in profile symbol list "
              "will be used. This is very useful for performance debugging"));
 
+cl::opt<bool> DuplicateContextProfilesIntoBaseProfile(
+    "duplicate-contexts-into-base", cl::init(true), cl::ZeroOrMore,
+    cl::desc("When converting a CS flat profile into a nested profile, "
+             "duplicating all context profiles of a function into its base "
+             "profile"));
+
 namespace llvm {
 namespace sampleprof {
 SampleProfileFormat FunctionSamples::Format;
 bool FunctionSamples::ProfileIsProbeBased = false;
 bool FunctionSamples::ProfileIsCS = false;
+bool FunctionSamples::ProfileIsPreinlined = false;
 bool FunctionSamples::UseMD5 = false;
 bool FunctionSamples::HasUniqSuffix = true;
 bool FunctionSamples::ProfileIsFS = false;
@@ -219,7 +226,7 @@
 }
 
 LineLocation FunctionSamples::getCallSiteIdentifier(const DILocation *DIL) {
-  if (FunctionSamples::ProfileIsProbeBased)
+  if (FunctionSamples::ProfileIsProbeBased) {
     // In a pseudo-probe based profile, a callsite is simply represented by the
     // ID of the probe associated with the call instruction. The probe ID is
     // encoded in the Discriminator field of the call instruction's debug
@@ -227,9 +234,22 @@
     return LineLocation(PseudoProbeDwarfDiscriminator::extractProbeIndex(
                             DIL->getDiscriminator()),
                         0);
-  else
-    return LineLocation(FunctionSamples::getOffset(DIL),
-                        DIL->getBaseDiscriminator());
+  } else {
+    unsigned Discriminator;
+    if (FunctionSamples::ProfileIsFS)
+      Discriminator = DIL->getDiscriminator();
+    else
+      Discriminator = DIL->getBaseDiscriminator();
+    return LineLocation(FunctionSamples::getOffset(DIL), Discriminator);
+  }
+}
+
+uint64_t FunctionSamples::getCallSiteHash(StringRef CalleeName,
+                                          const LineLocation &Callsite) {
+  uint64_t NameHash = std::hash<std::string>{}(CalleeName.str());
+  uint64_t LocId =
+      (((uint64_t)Callsite.LineOffset) << 32) | Callsite.Discriminator;
+  return NameHash + (LocId << 5) + LocId;
 }
 
 const FunctionSamples *FunctionSamples::findFunctionSamples(
@@ -239,21 +259,14 @@
 
   const DILocation *PrevDIL = DIL;
   for (DIL = DIL->getInlinedAt(); DIL; DIL = DIL->getInlinedAt()) {
-    unsigned Discriminator;
-    if (ProfileIsFS)
-      Discriminator = DIL->getDiscriminator();
-    else
-      Discriminator = DIL->getBaseDiscriminator();
-
     // Use C++ linkage name if possible.
     StringRef Name = PrevDIL->getScope()->getSubprogram()->getLinkageName();
     if (Name.empty())
       Name = PrevDIL->getScope()->getSubprogram()->getName();
-
-    S.push_back(
-        std::make_pair(LineLocation(getOffset(DIL), Discriminator), Name));
+    S.emplace_back(FunctionSamples::getCallSiteIdentifier(DIL), Name);
     PrevDIL = DIL;
   }
+
   if (S.size() == 0)
     return this;
   const FunctionSamples *FS = this;
@@ -454,3 +467,81 @@
   for (auto &Sym : SortedList)
     OS << Sym << "\n";
 }
+
+CSProfileConverter::FrameNode *
+CSProfileConverter::FrameNode::getOrCreateChildFrame(
+    const LineLocation &CallSite, StringRef CalleeName) {
+  uint64_t Hash = FunctionSamples::getCallSiteHash(CalleeName, CallSite);
+  auto It = AllChildFrames.find(Hash);
+  if (It != AllChildFrames.end()) {
+    assert(It->second.FuncName == CalleeName &&
+           "Hash collision for child context node");
+    return &It->second;
+  }
+
+  AllChildFrames[Hash] = FrameNode(CalleeName, nullptr, CallSite);
+  return &AllChildFrames[Hash];
+}
+
+CSProfileConverter::CSProfileConverter(SampleProfileMap &Profiles)
+    : ProfileMap(Profiles) {
+  for (auto &FuncSample : Profiles) {
+    FunctionSamples *FSamples = &FuncSample.second;
+    auto *NewNode = getOrCreateContextPath(FSamples->getContext());
+    assert(!NewNode->FuncSamples && "New node cannot have sample profile");
+    NewNode->FuncSamples = FSamples;
+  }
+}
+
+CSProfileConverter::FrameNode *
+CSProfileConverter::getOrCreateContextPath(const SampleContext &Context) {
+  auto Node = &RootFrame;
+  LineLocation CallSiteLoc(0, 0);
+  for (auto &Callsite : Context.getContextFrames()) {
+    Node = Node->getOrCreateChildFrame(CallSiteLoc, Callsite.FuncName);
+    CallSiteLoc = Callsite.Location;
+  }
+  return Node;
+}
+
+void CSProfileConverter::convertProfiles(CSProfileConverter::FrameNode &Node) {
+  // Process each child profile. Add each child profile to callsite profile map
+  // of the current node `Node` if `Node` comes with a profile. Otherwise
+  // promote the child profile to a standalone profile.
+  auto *NodeProfile = Node.FuncSamples;
+  for (auto &It : Node.AllChildFrames) {
+    auto &ChildNode = It.second;
+    convertProfiles(ChildNode);
+    auto *ChildProfile = ChildNode.FuncSamples;
+    if (!ChildProfile)
+      continue;
+    SampleContext OrigChildContext = ChildProfile->getContext();
+    // Reset the child context to be contextless.
+    ChildProfile->getContext().setName(OrigChildContext.getName());
+    if (NodeProfile) {
+      // Add child profile to the callsite profile map.
+      auto &SamplesMap = NodeProfile->functionSamplesAt(ChildNode.CallSiteLoc);
+      SamplesMap.emplace(OrigChildContext.getName(), *ChildProfile);
+      NodeProfile->addTotalSamples(ChildProfile->getTotalSamples());
+    }
+
+    // Separate child profile to be a standalone profile, if the current parent
+    // profile doesn't exist. This is a duplicating operation when the child
+    // profile is already incorporated into the parent which is still useful and
+    // thus done optionally. It is seen that duplicating context profiles into
+    // base profiles improves the code quality for thinlto build by allowing a
+    // profile in the prelink phase for to-be-fully-inlined functions.
+    if (!NodeProfile || DuplicateContextProfilesIntoBaseProfile)
+      ProfileMap[ChildProfile->getContext()].merge(*ChildProfile);
+
+    // Contexts coming with a `ContextShouldBeInlined` attribute indicate this
+    // is a preinliner-computed profile.
+    if (OrigChildContext.hasAttribute(ContextShouldBeInlined))
+      FunctionSamples::ProfileIsPreinlined = true;
+
+    // Remove the original child profile.
+    ProfileMap.erase(OrigChildContext);
+  }
+}
+
+void CSProfileConverter::convertProfiles() { convertProfiles(RootFrame); }
diff --git a/llvm/lib/ProfileData/SampleProfReader.cpp b/llvm/lib/ProfileData/SampleProfReader.cpp
--- a/llvm/lib/ProfileData/SampleProfReader.cpp
+++ b/llvm/lib/ProfileData/SampleProfReader.cpp
@@ -146,7 +146,7 @@
   if (Depth == 0)
     return false;
 
-  if (Depth == 1 && Input[Depth] == '!') {
+  if (Input[Depth] == '!') {
     LineTy = LineType::Metadata;
     return parseMetadata(Input.substr(Depth), FunctionHash, Attributes);
   }
@@ -248,7 +248,7 @@
 
   // SeenMetadata tracks whether we have processed metadata for the current
   // top-level function profile.
-  bool SeenMetadata = false;
+  uint32_t DepthMetadata = 0;
 
   ProfileIsFS = ProfileIsFSDisciminator;
   FunctionSamples::ProfileIsFS = ProfileIsFS;
@@ -275,7 +275,7 @@
                     "Expected 'mangled_name:NUM:NUM', found " + *LineIt);
         return sampleprof_error::malformed;
       }
-      SeenMetadata = false;
+      DepthMetadata = 0;
       SampleContext FContext(FName, CSNameTable);
       if (FContext.hasContext())
         ++CSProfileCount;
@@ -302,7 +302,7 @@
                         *LineIt);
         return sampleprof_error::malformed;
       }
-      if (SeenMetadata && LineTy != LineType::Metadata) {
+      if (LineTy != LineType::Metadata && Depth == DepthMetadata) {
         // Metadata must be put at the end of a function profile.
         reportError(LineIt.line_number(),
                     "Found non-metadata after metadata: " + *LineIt);
@@ -322,6 +322,7 @@
         FSamples.setName(FName);
         MergeResult(Result, FSamples.addTotalSamples(NumSamples));
         InlineStack.push_back(&FSamples);
+        DepthMetadata = 0;
         break;
       }
       case LineType::BodyProfile: {
@@ -342,11 +343,13 @@
         FunctionSamples &FProfile = *InlineStack.back();
         if (FunctionHash) {
           FProfile.setFunctionHash(FunctionHash);
-          ++ProbeProfileCount;
+          if (Depth == 1)
+            ++ProbeProfileCount;
         }
-        if (Attributes)
-          FProfile.getContext().setAllAttributes(Attributes);
-        SeenMetadata = true;
+        FProfile.getContext().setAllAttributes(Attributes);
+        if (Attributes & (uint32_t)ContextShouldBeInlined)
+          ProfileIsPreinlined = true;
+        DepthMetadata = Depth;
         break;
       }
       }
@@ -361,6 +364,7 @@
   ProfileIsProbeBased = (ProbeProfileCount > 0);
   FunctionSamples::ProfileIsProbeBased = ProfileIsProbeBased;
   FunctionSamples::ProfileIsCS = ProfileIsCS;
+  FunctionSamples::ProfileIsPreinlined = ProfileIsPreinlined;
 
   if (Result == sampleprof_error::success)
     computeSummary();
@@ -683,6 +687,9 @@
     ProfileIsProbeBased =
         hasSecFlag(Entry, SecFuncMetadataFlags::SecFlagIsProbeBased);
     FunctionSamples::ProfileIsProbeBased = ProfileIsProbeBased;
+    ProfileIsPreinlined =
+        hasSecFlag(Entry, SecFuncMetadataFlags::SecFlagIsPreInlined);
+    FunctionSamples::ProfileIsPreinlined = ProfileIsPreinlined;
     bool HasAttribute =
         hasSecFlag(Entry, SecFuncMetadataFlags::SecFlagHasAttribute);
     if (std::error_code EC = readFuncMetadata(HasAttribute))
@@ -1078,30 +1085,79 @@
 }
 
 std::error_code
-SampleProfileReaderExtBinaryBase::readFuncMetadata(bool ProfileHasAttribute) {
-  while (Data < End) {
-    auto FContext(readSampleContextFromTable());
-    if (std::error_code EC = FContext.getError())
-      return EC;
 
-    bool ProfileInMap = Profiles.count(*FContext);
+SampleProfileReaderExtBinaryBase::readFuncMetadata(bool ProfileHasAttribute,
+                                                   FunctionSamples *FProfile,
+                                                   bool Inlined) {
+  if (Data < End) {
     if (ProfileIsProbeBased) {
       auto Checksum = readNumber<uint64_t>();
       if (std::error_code EC = Checksum.getError())
         return EC;
-      if (ProfileInMap)
-        Profiles[*FContext].setFunctionHash(*Checksum);
+      if (FProfile)
+        FProfile->setFunctionHash(*Checksum);
     }
 
     if (ProfileHasAttribute) {
       auto Attributes = readNumber<uint32_t>();
       if (std::error_code EC = Attributes.getError())
         return EC;
-      if (ProfileInMap)
-        Profiles[*FContext].getContext().setAllAttributes(*Attributes);
+      if (FProfile)
+        FProfile->getContext().setAllAttributes(*Attributes);
+    }
+
+    if (!ProfileIsCS) {
+      // Read all the attributes for inlined function calls.
+      auto NumCallsites = readNumber<uint32_t>();
+      if (std::error_code EC = NumCallsites.getError())
+        return EC;
+
+      for (uint32_t J = 0; J < *NumCallsites; ++J) {
+        auto LineOffset = readNumber<uint64_t>();
+        if (std::error_code EC = LineOffset.getError())
+          return EC;
+
+        auto Discriminator = readNumber<uint64_t>();
+        if (std::error_code EC = Discriminator.getError())
+          return EC;
+
+        auto FContext(readSampleContextFromTable());
+        if (std::error_code EC = FContext.getError())
+          return EC;
+
+        FunctionSamples *CalleeProfile = nullptr;
+        if (FProfile) {
+          CalleeProfile = const_cast<FunctionSamples *>(
+              &FProfile->functionSamplesAt(LineLocation(
+                  *LineOffset,
+                  *Discriminator))[std::string(FContext.get().getName())]);
+        }
+        if (std::error_code EC =
+                readFuncMetadata(ProfileHasAttribute, CalleeProfile, true))
+          return EC;
+      }
     }
   }
 
+  return sampleprof_error::success;
+}
+
+std::error_code
+SampleProfileReaderExtBinaryBase::readFuncMetadata(bool ProfileHasAttribute) {
+  while (Data < End) {
+    auto FContext(readSampleContextFromTable());
+    if (std::error_code EC = FContext.getError())
+      return EC;
+    FunctionSamples *FProfile = nullptr;
+    auto It = Profiles.find(*FContext);
+    if (It != Profiles.end())
+      FProfile = &It->second;
+
+    if (std::error_code EC =
+            readFuncMetadata(ProfileHasAttribute, FProfile, false))
+      return EC;
+  }
+
   assert(Data == End && "More data is read than expected");
   return sampleprof_error::success;
 }
@@ -1233,6 +1289,8 @@
       Flags.append("probe,");
     if (hasSecFlag(Entry, SecFuncMetadataFlags::SecFlagHasAttribute))
       Flags.append("attr,");
+    if (hasSecFlag(Entry, SecFuncMetadataFlags::SecFlagIsPreInlined))
+      Flags.append("preinlined,");
     break;
   default:
     break;
diff --git a/llvm/lib/ProfileData/SampleProfWriter.cpp b/llvm/lib/ProfileData/SampleProfWriter.cpp
--- a/llvm/lib/ProfileData/SampleProfWriter.cpp
+++ b/llvm/lib/ProfileData/SampleProfWriter.cpp
@@ -194,18 +194,46 @@
   return sampleprof_error::success;
 }
 
+std::error_code SampleProfileWriterExtBinaryBase::writeFuncMetadata(
+    const FunctionSamples &FunctionProfile) {
+  auto &OS = *OutputStream;
+  if (std::error_code EC = writeContextIdx(FunctionProfile.getContext()))
+    return EC;
+
+  if (FunctionSamples::ProfileIsProbeBased)
+    encodeULEB128(FunctionProfile.getFunctionHash(), OS);
+  if (FunctionSamples::ProfileIsCS || FunctionSamples::ProfileIsPreinlined) {
+    encodeULEB128(FunctionProfile.getContext().getAllAttributes(), OS);
+  }
+
+  if (!FunctionSamples::ProfileIsCS) {
+    // Recursively emit attributes for all callee samples.
+    uint64_t NumCallsites = 0;
+    for (const auto &J : FunctionProfile.getCallsiteSamples())
+      NumCallsites += J.second.size();
+    encodeULEB128(NumCallsites, OS);
+    for (const auto &J : FunctionProfile.getCallsiteSamples()) {
+      for (const auto &FS : J.second) {
+        LineLocation Loc = J.first;
+        encodeULEB128(Loc.LineOffset, OS);
+        encodeULEB128(Loc.Discriminator, OS);
+        if (std::error_code EC = writeFuncMetadata(FS.second))
+          return EC;
+      }
+    }
+  }
+
+  return sampleprof_error::success;
+}
+
 std::error_code SampleProfileWriterExtBinaryBase::writeFuncMetadata(
     const SampleProfileMap &Profiles) {
-  if (!FunctionSamples::ProfileIsProbeBased && !FunctionSamples::ProfileIsCS)
+  if (!FunctionSamples::ProfileIsProbeBased && !FunctionSamples::ProfileIsCS &&
+      !FunctionSamples::ProfileIsPreinlined)
     return sampleprof_error::success;
-  auto &OS = *OutputStream;
   for (const auto &Entry : Profiles) {
-    if (std::error_code EC = writeContextIdx(Entry.second.getContext()))
+    if (std::error_code EC = writeFuncMetadata(Entry.second))
       return EC;
-    if (FunctionSamples::ProfileIsProbeBased)
-      encodeULEB128(Entry.second.getFunctionHash(), OS);
-    if (FunctionSamples::ProfileIsCS)
-      encodeULEB128(Entry.second.getContext().getAllAttributes(), OS);
   }
   return sampleprof_error::success;
 }
@@ -295,10 +323,13 @@
     setToCompressSection(SecProfileSymbolList);
   if (Type == SecFuncMetadata && FunctionSamples::ProfileIsProbeBased)
     addSectionFlag(SecFuncMetadata, SecFuncMetadataFlags::SecFlagIsProbeBased);
+  if (Type == SecFuncMetadata && FunctionSamples::ProfileIsPreinlined)
+    addSectionFlag(SecFuncMetadata, SecFuncMetadataFlags::SecFlagIsPreInlined);
+  if (Type == SecFuncMetadata &&
+      (FunctionSamples::ProfileIsCS || FunctionSamples::ProfileIsPreinlined))
+    addSectionFlag(SecFuncMetadata, SecFuncMetadataFlags::SecFlagHasAttribute);
   if (Type == SecProfSummary && FunctionSamples::ProfileIsCS)
     addSectionFlag(SecProfSummary, SecProfSummaryFlags::SecFlagFullContext);
-  if (Type == SecFuncMetadata && FunctionSamples::ProfileIsCS)
-    addSectionFlag(SecFuncMetadata, SecFuncMetadataFlags::SecFlagHasAttribute);
   if (Type == SecProfSummary && FunctionSamples::ProfileIsFS)
     addSectionFlag(SecProfSummary, SecProfSummaryFlags::SecFlagFSDiscriminator);
 
@@ -483,15 +514,14 @@
     }
   Indent -= 1;
 
-  if (Indent == 0) {
-    if (FunctionSamples::ProfileIsProbeBased) {
-      OS.indent(Indent + 1);
-      OS << "!CFGChecksum: " << S.getFunctionHash() << "\n";
-    }
-    if (FunctionSamples::ProfileIsCS) {
-      OS.indent(Indent + 1);
-      OS << "!Attributes: " << S.getContext().getAllAttributes() << "\n";
-    }
+  if (FunctionSamples::ProfileIsProbeBased) {
+    OS.indent(Indent + 1);
+    OS << "!CFGChecksum: " << S.getFunctionHash() << "\n";
+  }
+
+  if (S.getContext().getAllAttributes()) {
+    OS.indent(Indent + 1);
+    OS << "!Attributes: " << S.getContext().getAllAttributes() << "\n";
   }
 
   return sampleprof_error::success;
diff --git a/llvm/lib/Transforms/IPO/SampleContextTracker.cpp b/llvm/lib/Transforms/IPO/SampleContextTracker.cpp
--- a/llvm/lib/Transforms/IPO/SampleContextTracker.cpp
+++ b/llvm/lib/Transforms/IPO/SampleContextTracker.cpp
@@ -32,7 +32,7 @@
   if (CalleeName.empty())
     return getHottestChildContext(CallSite);
 
-  uint64_t Hash = nodeHash(CalleeName, CallSite);
+  uint64_t Hash = FunctionSamples::getCallSiteHash(CalleeName, CallSite);
   auto It = AllChildContext.find(Hash);
   if (It != AllChildContext.end())
     return &It->second;
@@ -65,7 +65,8 @@
 ContextTrieNode &ContextTrieNode::moveToChildContext(
     const LineLocation &CallSite, ContextTrieNode &&NodeToMove,
     uint32_t ContextFramesToRemove, bool DeleteNode) {
-  uint64_t Hash = nodeHash(NodeToMove.getFuncName(), CallSite);
+  uint64_t Hash =
+      FunctionSamples::getCallSiteHash(NodeToMove.getFuncName(), CallSite);
   assert(!AllChildContext.count(Hash) && "Node to remove must exist");
   LineLocation OldCallSite = NodeToMove.CallSiteLoc;
   ContextTrieNode &OldParentContext = *NodeToMove.getParentContext();
@@ -108,7 +109,7 @@
 
 void ContextTrieNode::removeChildContext(const LineLocation &CallSite,
                                          StringRef CalleeName) {
-  uint64_t Hash = nodeHash(CalleeName, CallSite);
+  uint64_t Hash = FunctionSamples::getCallSiteHash(CalleeName, CallSite);
   // Note this essentially calls dtor and destroys that child context
   AllChildContext.erase(Hash);
 }
@@ -174,21 +175,9 @@
   }
 }
 
-uint64_t ContextTrieNode::nodeHash(StringRef ChildName,
-                                   const LineLocation &Callsite) {
-  // We still use child's name for child hash, this is
-  // because for children of root node, we don't have
-  // different line/discriminator, and we'll rely on name
-  // to differentiate children.
-  uint64_t NameHash = std::hash<std::string>{}(ChildName.str());
-  uint64_t LocId =
-      (((uint64_t)Callsite.LineOffset) << 32) | Callsite.Discriminator;
-  return NameHash + (LocId << 5) + LocId;
-}
-
 ContextTrieNode *ContextTrieNode::getOrCreateChildContext(
     const LineLocation &CallSite, StringRef CalleeName, bool AllowCreate) {
-  uint64_t Hash = nodeHash(CalleeName, CallSite);
+  uint64_t Hash = FunctionSamples::getCallSiteHash(CalleeName, CallSite);
   auto It = AllChildContext.find(Hash);
   if (It != AllChildContext.end()) {
     assert(It->second.getFuncName() == CalleeName &&
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
@@ -467,6 +467,9 @@
   void emitOptimizationRemarksForInlineCandidates(
       const SmallVectorImpl<CallBase *> &Candidates, const Function &F,
       bool Hot);
+  void accumulateNonInlinedSamples(
+      DenseMap<CallBase *, const FunctionSamples *> NonInlinedCallSites,
+      const Function &F);
   std::vector<Function *> buildFunctionOrder(Module &M, CallGraph *CG);
   std::unique_ptr<ProfiledCallGraph> buildProfiledCallGraph(CallGraph &CG);
   void generateMDProfMetadata(Function &F);
@@ -1198,53 +1201,9 @@
   }
 
   // For CS profile, profile for not inlined context will be merged when
-  // base profile is being trieved
-  if (ProfileIsCS)
-    return Changed;
-
-  // Accumulate not inlined callsite information into notInlinedSamples
-  for (const auto &Pair : LocalNotInlinedCallSites) {
-    CallBase *I = Pair.getFirst();
-    Function *Callee = I->getCalledFunction();
-    if (!Callee || Callee->isDeclaration())
-      continue;
-
-    ORE->emit(OptimizationRemarkAnalysis(CSINLINE_DEBUG, "NotInline",
-                                         I->getDebugLoc(), I->getParent())
-              << "previous inlining not repeated: '"
-              << ore::NV("Callee", Callee) << "' into '"
-              << ore::NV("Caller", &F) << "'");
-
-    ++NumCSNotInlined;
-    const FunctionSamples *FS = Pair.getSecond();
-    if (FS->getTotalSamples() == 0 && FS->getEntrySamples() == 0) {
-      continue;
-    }
-
-    if (ProfileMergeInlinee) {
-      // A function call can be replicated by optimizations like callsite
-      // splitting or jump threading and the replicates end up sharing the
-      // sample nested callee profile instead of slicing the original inlinee's
-      // profile. We want to do merge exactly once by filtering out callee
-      // profiles with a non-zero head sample count.
-      if (FS->getHeadSamples() == 0) {
-        // Use entry samples as head samples during the merge, as inlinees
-        // don't have head samples.
-        const_cast<FunctionSamples *>(FS)->addHeadSamples(
-            FS->getEntrySamples());
-
-        // Note that we have to do the merge right after processing function.
-        // This allows OutlineFS's profile to be used for annotation during
-        // top-down processing of functions' annotation.
-        FunctionSamples *OutlineFS = Reader->getOrCreateSamplesFor(*Callee);
-        OutlineFS->merge(*FS);
-      }
-    } else {
-      auto pair =
-          notInlinedCallInfo.try_emplace(Callee, NotInlinedProfileInfo{0});
-      pair.first->second.entryCount += FS->getEntrySamples();
-    }
-  }
+  // base profile is being retrieved.
+  if (!FunctionSamples::ProfileIsCS)
+    accumulateNonInlinedSamples(LocalNotInlinedCallSites, F);
   return Changed;
 }
 
@@ -1430,7 +1389,6 @@
 
 bool SampleProfileLoader::inlineHotFunctionsWithPriority(
     Function &F, DenseSet<GlobalValue::GUID> &InlinedGUIDs) {
-  assert(ProfileIsCS && "Prioritiy based inliner only works with CSSPGO now");
 
   // ProfAccForSymsInList is used in callsiteIsHot. The assertion makes sure
   // Profile symbol list is ignored when profile-sample-accurate is on.
@@ -1467,6 +1425,8 @@
   if (ExternalInlineAdvisor)
     SizeLimit = std::numeric_limits<unsigned>::max();
 
+  DenseMap<CallBase *, const FunctionSamples *> LocalNotInlinedCallSites;
+
   // Perform iterative BFS call site prioritized inlining
   bool Changed = false;
   while (!CQueue.empty() && F.getInstructionCount() < SizeLimit) {
@@ -1521,6 +1481,8 @@
           }
           ICPCount++;
           Changed = true;
+        } else if (FunctionSamples::ProfileIsPreinlined) {
+          LocalNotInlinedCallSites.try_emplace(I, FS);
         }
       }
     } else if (CalledFunction && CalledFunction->getSubprogram() &&
@@ -1532,6 +1494,8 @@
             CQueue.emplace(NewCandidate);
         }
         Changed = true;
+      } else if (FunctionSamples::ProfileIsPreinlined) {
+        LocalNotInlinedCallSites.try_emplace(I, Candidate.CalleeSamples);
       }
     } else if (LTOPhase == ThinOrFullLTOPhase::ThinLTOPreLink) {
       findExternalInlineCandidate(I, findCalleeFunctionSamples(*I),
@@ -1549,9 +1513,63 @@
       ++NumCSInlinedHitGrowthLimit;
   }
 
+  // For CS profile, profile for not inlined context will be merged when
+  // base profile is being retrieved.
+  if (!FunctionSamples::ProfileIsCS)
+    accumulateNonInlinedSamples(LocalNotInlinedCallSites, F);
   return Changed;
 }
 
+void SampleProfileLoader::accumulateNonInlinedSamples(
+    DenseMap<CallBase *, const FunctionSamples *> NonInlinedCallSites,
+    const Function &F) {
+  // Accumulate not inlined callsite information into notInlinedSamples
+  for (const auto &Pair : NonInlinedCallSites) {
+    CallBase *I = Pair.getFirst();
+    Function *Callee = I->getCalledFunction();
+    if (!Callee || Callee->isDeclaration())
+      continue;
+
+    ORE->emit(OptimizationRemarkAnalysis(CSINLINE_DEBUG, "NotInline",
+                                         I->getDebugLoc(), I->getParent())
+              << "previous inlining not repeated: '"
+              << ore::NV("Callee", Callee) << "' into '"
+              << ore::NV("Caller", &F) << "'");
+
+    ++NumCSNotInlined;
+    const FunctionSamples *FS = Pair.getSecond();
+    if (FS->getTotalSamples() == 0 && FS->getEntrySamples() == 0) {
+      continue;
+    }
+
+    if (ProfileMergeInlinee) {
+      // A function call can be replicated by optimizations like callsite
+      // splitting or jump threading and the replicates end up sharing the
+      // sample nested callee profile instead of slicing the original
+      // inlinee's profile. We want to do merge exactly once by filtering out
+      // callee profiles with a non-zero head sample count.
+      if (FS->getHeadSamples() == 0) {
+        // Use entry samples as head samples during the merge, as inlinees
+        // don't have head samples.
+        const_cast<FunctionSamples *>(FS)->addHeadSamples(
+            FS->getEntrySamples());
+
+        // Note that we have to do the merge right after processing function.
+        // This allows OutlineFS's profile to be used for annotation during
+        // top-down processing of functions' annotation.
+        FunctionSamples *OutlineFS = Reader->getOrCreateSamplesFor(*Callee);
+        OutlineFS->merge(*FS, 1);
+        // Set outlined profile to be synthetic to not bias the inliner.
+        OutlineFS->SetContextSynthetic();
+      }
+    } else {
+      auto pair =
+          notInlinedCallInfo.try_emplace(Callee, NotInlinedProfileInfo{0});
+      pair.first->second.entryCount += FS->getEntrySamples();
+    }
+  }
+}
+
 /// Returns the sorted CallTargetMap \p M by count in descending order.
 static SmallVector<InstrProfValueData, 2>
 GetSortedValueDataFromCallTargets(const SampleRecord::CallTargetMap &M) {
@@ -1754,7 +1772,7 @@
   }
 
   DenseSet<GlobalValue::GUID> InlinedGUIDs;
-  if (ProfileIsCS && CallsitePrioritizedInline)
+  if (CallsitePrioritizedInline)
     Changed |= inlineHotFunctionsWithPriority(F, InlinedGUIDs);
   else
     Changed |= inlineHotFunctions(F, InlinedGUIDs);
@@ -1961,10 +1979,8 @@
   }
 
   // Apply tweaks if context-sensitive profile is available.
-  if (Reader->profileIsCS()) {
-    ProfileIsCS = true;
-    FunctionSamples::ProfileIsCS = true;
-
+  if (Reader->profileIsCS() || Reader->profileIsPreinlined()) {
+    ProfileIsCS = Reader->profileIsCS();
     // Enable priority-base inliner and size inline by default for CSSPGO.
     if (!ProfileSizeInline.getNumOccurrences())
       ProfileSizeInline = true;
@@ -1986,9 +2002,11 @@
     if (!SampleProfileUseProfi.getNumOccurrences())
       SampleProfileUseProfi = true;
 
-    // Tracker for profiles under different context
-    ContextTracker = std::make_unique<SampleContextTracker>(
-        Reader->getProfiles(), &GUIDToFuncNameMap);
+    if (FunctionSamples::ProfileIsCS) {
+      // Tracker for profiles under different context
+      ContextTracker = std::make_unique<SampleContextTracker>(
+          Reader->getProfiles(), &GUIDToFuncNameMap);
+    }
   }
 
   // Load pseudo probe descriptors for probe-based function samples.
diff --git a/llvm/test/Transforms/SampleProfile/csspgo-inline.ll b/llvm/test/Transforms/SampleProfile/csspgo-inline.ll
--- a/llvm/test/Transforms/SampleProfile/csspgo-inline.ll
+++ b/llvm/test/Transforms/SampleProfile/csspgo-inline.ll
@@ -10,8 +10,12 @@
 ; RUN: llvm-profdata merge --sample --extbinary --use-md5 %S/Inputs/profile-context-tracker.prof -o %t.md5
 ; RUN: opt < %s -passes=sample-profile -sample-profile-file=%t.md5 -sample-profile-inline-size -sample-profile-prioritized-inline=0 -profile-sample-accurate -S -pass-remarks=inline -o /dev/null 2>&1 | FileCheck %s --check-prefix=INLINE-BASE
 
+; RUN: llvm-profdata merge --sample --text --gen-nested-profile %S/Inputs/profile-context-tracker.prof -o %t.prof
+; RUN: opt < %s -passes=sample-profile -sample-profile-file=%t.prof -sample-profile-inline-size -sample-profile-prioritized-inline=0 -profile-sample-accurate -S -pass-remarks=inline -o /dev/null 2>&1 | FileCheck %s --check-prefix=INLINE-BASE
+
 ; With new FDO early inliner, callee entry count is used to drive inlining instead of callee total samples, so we get less inlining for given profile
 ; RUN: opt < %s -passes=sample-profile -sample-profile-file=%S/Inputs/profile-context-tracker.prof -sample-profile-inline-size -profile-sample-accurate -S -pass-remarks=inline -o /dev/null 2>&1 | FileCheck %s --check-prefix=INLINE-NEW
+; RUN: opt < %s -passes=sample-profile -sample-profile-file=%t.prof -sample-profile-prioritized-inline -sample-profile-inline-size -profile-sample-accurate -S -pass-remarks=inline -o /dev/null 2>&1 | FileCheck %s --check-prefix=INLINE-NEW
 ;
 ; With new FDO early inliner, callee entry count is used to drive inlining instead of callee total samples, tuning hot cutoff can get us the same inlining
 ; RUN: opt < %s -passes=sample-profile -sample-profile-file=%S/Inputs/profile-context-tracker.prof -sample-profile-inline-size -profile-summary-cutoff-hot=999900 -profile-sample-accurate -S -pass-remarks=inline -o /dev/null 2>&1 | FileCheck %s --check-prefix=INLINE-BASE
diff --git a/llvm/test/Transforms/SampleProfile/csspgo-use-preinliner.ll b/llvm/test/Transforms/SampleProfile/csspgo-use-preinliner.ll
--- a/llvm/test/Transforms/SampleProfile/csspgo-use-preinliner.ll
+++ b/llvm/test/Transforms/SampleProfile/csspgo-use-preinliner.ll
@@ -3,6 +3,9 @@
 ; RUN: opt < %s -passes=sample-profile -sample-profile-file=%S/Inputs/csspgo-use-preinliner.prof -pass-remarks=inline -sample-profile-prioritized-inline -profile-sample-accurate -sample-profile-use-preinliner=0 -S 2>&1 | FileCheck %s --check-prefix=DEFAULT
 ; RUN: opt < %s -passes=sample-profile -sample-profile-file=%S/Inputs/csspgo-use-preinliner.prof -pass-remarks=inline -sample-profile-prioritized-inline -profile-sample-accurate -sample-profile-use-preinliner=1 -S 2>&1 | FileCheck %s --check-prefix=PREINLINE
 
+; RUN: llvm-profdata merge --sample --text --gen-nested-profile -duplicate-contexts-into-base=0 %S/Inputs/csspgo-use-preinliner.prof -o %t.prof
+; RUN: opt < %s -passes=sample-profile -sample-profile-file=%t.prof -pass-remarks=inline -sample-profile-prioritized-inline -profile-sample-accurate -sample-profile-use-preinliner=0 -S 2>&1 | FileCheck %s --check-prefix=DEFAULT
+; RUN: opt < %s -passes=sample-profile -sample-profile-file=%t.prof -pass-remarks=inline -sample-profile-prioritized-inline -profile-sample-accurate -sample-profile-use-preinliner=1 -S 2>&1 | FileCheck %s --check-prefix=PREINLINE
 
 ; DEFAULT: '_Z5funcAi' inlined into 'main'
 ; DEFAULT-NOT: inlined into
diff --git a/llvm/test/tools/llvm-profdata/Inputs/cs-sample.proftext b/llvm/test/tools/llvm-profdata/Inputs/cs-sample-preinline.proftext
copy from llvm/test/tools/llvm-profdata/Inputs/cs-sample.proftext
copy to llvm/test/tools/llvm-profdata/Inputs/cs-sample-preinline.proftext
--- a/llvm/test/tools/llvm-profdata/Inputs/cs-sample.proftext
+++ b/llvm/test/tools/llvm-profdata/Inputs/cs-sample-preinline.proftext
@@ -4,7 +4,7 @@
  3: 287884
  4: 287864 _Z3fibi:315608
  15: 23
- !Attributes: 0
+ !Attributes: 2
 [main:3.1 @ _Z5funcBi:1 @ _Z8funcLeafi]:500853:20
  0: 15
  1: 15
@@ -13,32 +13,28 @@
  10: 23324
  11: 23327 _Z3fibi:25228
  15: 11
- !Attributes: 1
+ !Attributes: 2
 [external:12 @ main]:154:12
  2: 12
  3: 10 _Z5funcAi:7
  3.1: 10 _Z5funcBi:11
- !Attributes: 0
 [main]:154:0
  2: 12
  3: 18 _Z5funcAi:11
  3.1: 18 _Z5funcBi:19
- !Attributes: 0
 [external:10 @ _Z5funcBi]:120:10
  0: 10
  1: 10
- !Attributes: 0
 [externalA:17 @ _Z5funcBi]:120:3
  0: 3
  1: 3
- !Attributes: 0
 [main:3.1 @ _Z5funcBi]:120:19
  0: 19
  1: 19 _Z8funcLeafi:20
  3: 12
- !Attributes: 1
+ !Attributes: 2
 [main:3 @ _Z5funcAi]:99:11
  0: 10
  1: 10 _Z8funcLeafi:11
  3: 24
- !Attributes: 0
+ !Attributes: 2
diff --git a/llvm/test/tools/llvm-profdata/Inputs/cs-sample.proftext b/llvm/test/tools/llvm-profdata/Inputs/cs-sample.proftext
--- a/llvm/test/tools/llvm-profdata/Inputs/cs-sample.proftext
+++ b/llvm/test/tools/llvm-profdata/Inputs/cs-sample.proftext
@@ -4,7 +4,6 @@
  3: 287884
  4: 287864 _Z3fibi:315608
  15: 23
- !Attributes: 0
 [main:3.1 @ _Z5funcBi:1 @ _Z8funcLeafi]:500853:20
  0: 15
  1: 15
@@ -18,20 +17,16 @@
  2: 12
  3: 10 _Z5funcAi:7
  3.1: 10 _Z5funcBi:11
- !Attributes: 0
 [main]:154:0
  2: 12
  3: 18 _Z5funcAi:11
  3.1: 18 _Z5funcBi:19
- !Attributes: 0
 [external:10 @ _Z5funcBi]:120:10
  0: 10
  1: 10
- !Attributes: 0
 [externalA:17 @ _Z5funcBi]:120:3
  0: 3
  1: 3
- !Attributes: 0
 [main:3.1 @ _Z5funcBi]:120:19
  0: 19
  1: 19 _Z8funcLeafi:20
@@ -41,4 +36,3 @@
  0: 10
  1: 10 _Z8funcLeafi:11
  3: 24
- !Attributes: 0
diff --git a/llvm/test/tools/llvm-profdata/cs-sample-nested-profile.test b/llvm/test/tools/llvm-profdata/cs-sample-nested-profile.test
new file mode 100644
--- /dev/null
+++ b/llvm/test/tools/llvm-profdata/cs-sample-nested-profile.test
@@ -0,0 +1,113 @@
+RUN: llvm-profdata merge --sample --text -output=%t.proftext %S/Inputs/cs-sample-preinline.proftext --gen-nested-profile=1 -duplicate-contexts-into-base=0
+RUN: FileCheck %s < %t.proftext --match-full-lines --strict-whitespace
+RUN: llvm-profdata merge --sample --extbinary -output=%t.profbin %S/Inputs/cs-sample-preinline.proftext --gen-nested-profile=1 -duplicate-contexts-into-base=0
+RUN: llvm-profdata merge --sample --text -output=%t2.proftext %t.profbin
+RUN: FileCheck %s < %t2.proftext --match-full-lines --strict-whitespace
+RUN: llvm-profdata show --sample -show-sec-info-only %t.profbin | FileCheck %s -check-prefix=PREINLINE
+RUN: llvm-profdata merge --sample --text -output=%t.proftext %S/Inputs/cs-sample-preinline.proftext --gen-nested-profile=1 -duplicate-contexts-into-base=1
+RUN: FileCheck %s < %t.proftext --match-full-lines --strict-whitespace -check-prefix=RECOUNT
+
+
+; CHECK:main:1968679:12
+; CHECK-NEXT: 2: 24
+; CHECK-NEXT: 3: 28 _Z5funcAi:18
+; CHECK-NEXT: 3.1: 28 _Z5funcBi:30
+; CHECK-NEXT: 3: _Z5funcAi:1467398
+; CHECK-NEXT:  0: 10
+; CHECK-NEXT:  1: 10 _Z8funcLeafi:11
+; CHECK-NEXT:  3: 24
+; CHECK-NEXT:  1: _Z8funcLeafi:1467299
+; CHECK-NEXT:   0: 6
+; CHECK-NEXT:   1: 6
+; CHECK-NEXT:   3: 287884
+; CHECK-NEXT:   4: 287864 _Z3fibi:315608
+; CHECK-NEXT:   15: 23
+; CHECK-NEXT:   !Attributes: 2
+; CHECK-NEXT:  !Attributes: 2
+; CHECK-NEXT: 3.1: _Z5funcBi:500973
+; CHECK-NEXT:  0: 19
+; CHECK-NEXT:  1: 19 _Z8funcLeafi:20
+; CHECK-NEXT:  3: 12
+; CHECK-NEXT:  1: _Z8funcLeafi:500853
+; CHECK-NEXT:   0: 15
+; CHECK-NEXT:   1: 15
+; CHECK-NEXT:   3: 74946
+; CHECK-NEXT:   4: 74941 _Z3fibi:82359
+; CHECK-NEXT:   10: 23324
+; CHECK-NEXT:   11: 23327 _Z3fibi:25228
+; CHECK-NEXT:   15: 11
+; CHECK-NEXT:   !Attributes: 2
+; CHECK-NEXT:  !Attributes: 2
+; CHECK-NEXT:_Z5funcBi:240:13
+; CHECK-NEXT: 0: 13
+; CHECK-NEXT: 1: 13
+
+
+
+; RECOUNT:main:1968679:12
+; RECOUNT-NEXT: 2: 24
+; RECOUNT-NEXT: 3: 28 _Z5funcAi:18
+; RECOUNT-NEXT: 3.1: 28 _Z5funcBi:30
+; RECOUNT-NEXT: 3: _Z5funcAi:1467398
+; RECOUNT-NEXT:  0: 10
+; RECOUNT-NEXT:  1: 10 _Z8funcLeafi:11
+; RECOUNT-NEXT:  3: 24
+; RECOUNT-NEXT:  1: _Z8funcLeafi:1467299
+; RECOUNT-NEXT:   0: 6
+; RECOUNT-NEXT:   1: 6
+; RECOUNT-NEXT:   3: 287884
+; RECOUNT-NEXT:   4: 287864 _Z3fibi:315608
+; RECOUNT-NEXT:   15: 23
+; RECOUNT-NEXT:   !Attributes: 2
+; RECOUNT-NEXT:  !Attributes: 2
+; RECOUNT-NEXT: 3.1: _Z5funcBi:500973
+; RECOUNT-NEXT:  0: 19
+; RECOUNT-NEXT:  1: 19 _Z8funcLeafi:20
+; RECOUNT-NEXT:  3: 12
+; RECOUNT-NEXT:  1: _Z8funcLeafi:500853
+; RECOUNT-NEXT:   0: 15
+; RECOUNT-NEXT:   1: 15
+; RECOUNT-NEXT:   3: 74946
+; RECOUNT-NEXT:   4: 74941 _Z3fibi:82359
+; RECOUNT-NEXT:   10: 23324
+; RECOUNT-NEXT:   11: 23327 _Z3fibi:25228
+; RECOUNT-NEXT:   15: 11
+; RECOUNT-NEXT:   !Attributes: 2
+; RECOUNT-NEXT:  !Attributes: 2
+; RECOUNT-NEXT:_Z8funcLeafi:1968152:31
+; RECOUNT-NEXT: 0: 21
+; RECOUNT-NEXT: 1: 21
+; RECOUNT-NEXT: 3: 362830
+; RECOUNT-NEXT: 4: 362805 _Z3fibi:397967
+; RECOUNT-NEXT: 10: 23324
+; RECOUNT-NEXT: 11: 23327 _Z3fibi:25228
+; RECOUNT-NEXT: 15: 34
+; RECOUNT-NEXT: !Attributes: 2
+; RECOUNT-NEXT:_Z5funcAi:1467398:11
+; RECOUNT-NEXT: 0: 10
+; RECOUNT-NEXT: 1: 10 _Z8funcLeafi:11
+; RECOUNT-NEXT: 3: 24
+; RECOUNT-NEXT: 1: _Z8funcLeafi:1467299
+; RECOUNT-NEXT:  0: 6
+; RECOUNT-NEXT:  1: 6
+; RECOUNT-NEXT:  3: 287884
+; RECOUNT-NEXT:  4: 287864 _Z3fibi:315608
+; RECOUNT-NEXT:  15: 23
+; RECOUNT-NEXT:  !Attributes: 2
+; RECOUNT-NEXT: !Attributes: 2
+; RECOUNT-NEXT:_Z5funcBi:501213:32
+; RECOUNT-NEXT: 0: 32
+; RECOUNT-NEXT: 1: 32 _Z8funcLeafi:20
+; RECOUNT-NEXT: 3: 12
+; RECOUNT-NEXT: 1: _Z8funcLeafi:500853
+; RECOUNT-NEXT:  0: 15
+; RECOUNT-NEXT:  1: 15
+; RECOUNT-NEXT:  3: 74946
+; RECOUNT-NEXT:  4: 74941 _Z3fibi:82359
+; RECOUNT-NEXT:  10: 23324
+; RECOUNT-NEXT:  11: 23327 _Z3fibi:25228
+; RECOUNT-NEXT:  15: 11
+; RECOUNT-NEXT:  !Attributes: 2
+
+
+; PREINLINE: FunctionMetadata {{.*}} Flags: {attr,preinlined}
diff --git a/llvm/test/tools/llvm-profdata/cs-sample-trimmer.test b/llvm/test/tools/llvm-profdata/cs-sample-trimmer.test
--- a/llvm/test/tools/llvm-profdata/cs-sample-trimmer.test
+++ b/llvm/test/tools/llvm-profdata/cs-sample-trimmer.test
@@ -14,7 +14,6 @@
 CHECK-TRIM-NEXT:  3: 287884
 CHECK-TRIM-NEXT:  4: 287864 _Z3fibi:315608
 CHECK-TRIM-NEXT:  15: 23
-CHECK-TRIM-NEXT:  !Attributes: 0
 CHECK-TRIM-NEXT: [main:3.1 @ _Z5funcBi:1 @ _Z8funcLeafi]:500853:20
 CHECK-TRIM-NEXT:  0: 15
 CHECK-TRIM-NEXT:  1: 15
@@ -29,14 +28,11 @@
 CHECK-MERGE-NEXT: 0: 32
 CHECK-MERGE-NEXT: 1: 32 _Z8funcLeafi:20
 CHECK-MERGE-NEXT: 3: 12
-CHECK-MERGE-NEXT: !Attributes: 0
 CHECK-MERGE-NEXT:[main]:308:12
 CHECK-MERGE-NEXT: 2: 24
 CHECK-MERGE-NEXT: 3: 28 _Z5funcAi:18
 CHECK-MERGE-NEXT: 3.1: 28 _Z5funcBi:30
-CHECK-MERGE-NEXT: !Attributes: 0
 CHECK-MERGE-NEXT:[_Z5funcAi]:99:11
 CHECK-MERGE-NEXT: 0: 10
 CHECK-MERGE-NEXT: 1: 10 _Z8funcLeafi:11
 CHECK-MERGE-NEXT: 3: 24
-CHECK-MERGE-NEXT: !Attributes: 0
diff --git a/llvm/test/tools/llvm-profgen/cs-preinline.test b/llvm/test/tools/llvm-profgen/cs-preinline.test
--- a/llvm/test/tools/llvm-profgen/cs-preinline.test
+++ b/llvm/test/tools/llvm-profgen/cs-preinline.test
@@ -15,6 +15,10 @@
 
 ; RUN: FileCheck %s --input-file %t --check-prefix=CHECK-TRIM
 
+; Test llvm-profgen with preinliner on will merge not inlinable profile into base profile.
+; RUN: llvm-profgen --format=text --perfscript=%S/Inputs/inline-cs-noprobe.perfscript --binary=%S/Inputs/inline-cs-noprobe.perfbin --output=%t --csspgo-preinliner=1 --gen-nested-profile=1
+; RUN: FileCheck %s --input-file %t --check-prefix=CHECK-PREINL-NEST
+
 ; CHECK-DEFAULT:     [main:1 @ foo]:44:0
 ; CHECK-DEFAULT-NEXT: 2.1: 14
 ; CHECK-DEFAULT-NEXT: 3: 15
@@ -49,3 +53,11 @@
 ; CHECK-TRIM:[foo:3.1 @ bar]:14:0
 ; CHECK-TRIM-NEXT: 1: 14
 ; CHECK-TRIM-NEXT: !Attributes: 3
+
+; CHECK-PREINL-NEST:     foo:58:0
+; CHECK-PREINL-NEST-NEXT: 2.1: 14
+; CHECK-PREINL-NEST-NEXT: 3: 15
+; CHECK-PREINL-NEST-NEXT: 3.1: 14 bar:14
+; CHECK-PREINL-NEST-NEXT: 3.2: 1
+; CHECK-PREINL-NEST-NEXT: 3.1: bar:14
+; CHECK-PREINL-NEST-NEXT:  1: 14
diff --git a/llvm/test/tools/llvm-profgen/merge-cold-profile.test b/llvm/test/tools/llvm-profgen/merge-cold-profile.test
--- a/llvm/test/tools/llvm-profgen/merge-cold-profile.test
+++ b/llvm/test/tools/llvm-profgen/merge-cold-profile.test
@@ -23,7 +23,6 @@
 ; CHECK-NEXT: 7: 2 fb:2
 ; CHECK-NEXT: 8: 1 fa:1
 ; CHECK-NEXT: !CFGChecksum: 563070469352221
-; CHECK-NEXT: !Attributes: 0
 ; CHECK-NEXT:[main:2 @ foo:5 @ fa:8 @ fa:7 @ fb:5 @ fb]:13:4
 ; CHECK-NEXT: 1: 4
 ; CHECK-NEXT: 2: 3
@@ -41,7 +40,6 @@
 ; CHECK-KEEP-COLD-NEXT: 5: 4 fb:4
 ; CHECK-KEEP-COLD-NEXT: 6: 3 fa:3
 ; CHECK-KEEP-COLD-NEXT: !CFGChecksum: 563022570642068
-; CHECK-KEEP-COLD-NEXT: !Attributes: 0
 ; CHECK-KEEP-COLD-NEXT:[fa]:14:4
 ; CHECK-KEEP-COLD-NEXT: 1: 4
 ; CHECK-KEEP-COLD-NEXT: 3: 4
@@ -71,7 +69,6 @@
 ; CHECK-COLD-CONTEXT-LENGTH-NEXT: 5: 4 fb:4
 ; CHECK-COLD-CONTEXT-LENGTH-NEXT: 6: 1 fa:1
 ; CHECK-COLD-CONTEXT-LENGTH-NEXT: !CFGChecksum: 563022570642068
-; CHECK-COLD-CONTEXT-LENGTH-NEXT: !Attributes: 0
 ; CHECK-COLD-CONTEXT-LENGTH-NEXT:[fb:6 @ fa]:10:3
 ; CHECK-COLD-CONTEXT-LENGTH-NEXT: 1: 3
 ; CHECK-COLD-CONTEXT-LENGTH-NEXT: 3: 3
@@ -81,7 +78,6 @@
 ; CHECK-COLD-CONTEXT-LENGTH-NEXT: 7: 1 fb:1
 ; CHECK-COLD-CONTEXT-LENGTH-NEXT: 8: 1 fa:1
 ; CHECK-COLD-CONTEXT-LENGTH-NEXT: !CFGChecksum: 563070469352221
-; CHECK-COLD-CONTEXT-LENGTH-NEXT: !Attributes: 0
 ; CHECK-COLD-CONTEXT-LENGTH-NEXT:[fa:7 @ fb]:6:2
 ; CHECK-COLD-CONTEXT-LENGTH-NEXT: 1: 2
 ; CHECK-COLD-CONTEXT-LENGTH-NEXT: 2: 0
@@ -90,7 +86,6 @@
 ; CHECK-COLD-CONTEXT-LENGTH-NEXT: 5: 0
 ; CHECK-COLD-CONTEXT-LENGTH-NEXT: 6: 2 fa:2
 ; CHECK-COLD-CONTEXT-LENGTH-NEXT: !CFGChecksum: 563022570642068
-; CHECK-COLD-CONTEXT-LENGTH-NEXT: !Attributes: 0
 ; CHECK-COLD-CONTEXT-LENGTH-NEXT:[fa:8 @ fa]:4:1
 ; CHECK-COLD-CONTEXT-LENGTH-NEXT: 1: 1
 ; CHECK-COLD-CONTEXT-LENGTH-NEXT: 3: 1
@@ -100,7 +95,6 @@
 ; CHECK-COLD-CONTEXT-LENGTH-NEXT: 7: 1 fb:1
 ; CHECK-COLD-CONTEXT-LENGTH-NEXT: 8: 0
 ; CHECK-COLD-CONTEXT-LENGTH-NEXT: !CFGChecksum: 563070469352221
-; CHECK-COLD-CONTEXT-LENGTH-NEXT: !Attributes: 0
 
 ; clang -O3 -fexperimental-new-pass-manager -fuse-ld=lld -fpseudo-probe-for-profiling
 ; -fno-omit-frame-pointer -mno-omit-leaf-frame-pointer -Xclang -mdisable-tail-calls
diff --git a/llvm/test/tools/llvm-profgen/truncated-pseudoprobe.test b/llvm/test/tools/llvm-profgen/truncated-pseudoprobe.test
--- a/llvm/test/tools/llvm-profgen/truncated-pseudoprobe.test
+++ b/llvm/test/tools/llvm-profgen/truncated-pseudoprobe.test
@@ -12,7 +12,6 @@
 ; CHECK-NEXT:  8: 15 bar:15
 ; CHECK-NEXT:  9: 0
 ; CHECK-NEXT:  !CFGChecksum: 563088904013236
-; CHECK-NEXT:  !Attributes: 0
 ; CHECK:     [foo:8 @ bar]:30:15
 ; CHECK-NEXT:  1: 15
 ; CHECK-NEXT:  4: 15
diff --git a/llvm/tools/llvm-profdata/llvm-profdata.cpp b/llvm/tools/llvm-profdata/llvm-profdata.cpp
--- a/llvm/tools/llvm-profdata/llvm-profdata.cpp
+++ b/llvm/tools/llvm-profdata/llvm-profdata.cpp
@@ -687,7 +687,7 @@
 mergeSampleProfile(const WeightedFileVector &Inputs, SymbolRemapper *Remapper,
                    StringRef OutputFilename, ProfileFormat OutputFormat,
                    StringRef ProfileSymbolListFile, bool CompressAllSections,
-                   bool UseMD5, bool GenPartialProfile,
+                   bool UseMD5, bool GenPartialProfile, bool GenNestedProfile,
                    bool SampleMergeColdContext, bool SampleTrimColdContext,
                    bool SampleColdContextFrameDepth, FailureMode FailMode) {
   using namespace sampleprof;
@@ -742,6 +742,12 @@
       }
     }
 
+    if (ProfileIsCS && GenNestedProfile) {
+      CSProfileConverter CSConverter(ProfileMap);
+      CSConverter.convertProfiles();
+      ProfileIsCS = FunctionSamples::ProfileIsCS = false;
+    }
+
     std::unique_ptr<sampleprof::ProfileSymbolList> ReaderList =
         Reader->getProfileSymbolList();
     if (ReaderList)
@@ -941,7 +947,10 @@
   cl::opt<unsigned> InstrProfColdThreshold(
       "instr-prof-cold-threshold", cl::init(0), cl::Hidden,
       cl::desc("User specified cold threshold for instr profile which will "
-               "override the cold threshold got from profile summary."));
+               "override the cold threshold got from profile summary. "));
+  cl::opt<bool> GenNestedProfile(
+      "gen-nested-profile", cl::Hidden, cl::init(false),
+      cl::desc("Generate nested function profiles for CSSPGO"));
 
   cl::ParseCommandLineOptions(argc, argv, "LLVM profile data merger\n");
 
@@ -987,10 +996,9 @@
   else
     mergeSampleProfile(WeightedInputs, Remapper.get(), OutputFilename,
                        OutputFormat, ProfileSymbolListFile, CompressAllSections,
-                       UseMD5, GenPartialProfile, SampleMergeColdContext,
-                       SampleTrimColdContext, SampleColdContextFrameDepth,
-                       FailureMode);
-
+                       UseMD5, GenPartialProfile, GenNestedProfile,
+                       SampleMergeColdContext, SampleTrimColdContext,
+                       SampleColdContextFrameDepth, FailureMode);
   return 0;
 }
 
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
@@ -83,6 +83,10 @@
 
 extern cl::opt<int> ProfileSummaryCutoffHot;
 
+static cl::opt<bool>
+    GenNestedProfile("gen-nested-profile", cl::Hidden, cl::init(false),
+                     cl::desc("Generate nested function profiles for CSSPGO"));
+
 using namespace llvm;
 using namespace sampleprof;
 
@@ -746,6 +750,12 @@
   }
 
   calculateAndShowDensity(ContextLessProfiles);
+  if (GenNestedProfile) {
+    CSProfileConverter CSConverter(ProfileMap);
+    CSConverter.convertProfiles();
+    FunctionSamples::ProfileIsCS = false;
+    FunctionSamples::ProfileIsPreinlined = EnableCSPreInliner;
+  }
 }
 
 void ProfileGeneratorBase::computeSummaryAndThreshold() {